Daily Papers

In this paper we describe our efforts to make a bidirectional Congolese Swahili (SWC) to French (FRA) neural machine translation system with the motivation of improving humanitarian translation workflows. For training, we created a 25,302-sentence general domain parallel corpus and combined it with publicly available data. Experimenting with low-resource methodologies like cross-dialect transfer and semi-supervised learning, we recorded improvements of up to 2.4 and 3.5 BLEU points in the SWC-FRA and FRA-SWC directions, respectively. We performed human evaluations to assess the usability of our models in a COVID-domain chatbot that operates in the Democratic Republic of Congo (DRC). Direct assessment in the SWC-FRA direction demonstrated an average quality ranking of 6.3 out of 10 with 75% of the target strings conveying the main message of the source text. For the FRA-SWC direction, our preliminary tests on post-editing assessment showed its potential usefulness for machine-assisted translation. We make our models, datasets containing up to 1 million sentences, our development pipeline, and a translator web-app available for public use.

Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs. However, concerns including transparency, controllability, and affordability strongly motivate the development of open-source LMs specialized in evaluations. On the other hand, existing open evaluator LMs exhibit critical shortcomings: 1) they issue scores that significantly diverge from those assigned by humans, and 2) they lack the flexibility to perform both direct assessment and pairwise ranking, the two most prevalent forms of assessment. Additionally, they do not possess the ability to evaluate based on custom evaluation criteria, focusing instead on general attributes like helpfulness and harmlessness. To address these issues, we introduce Prometheus 2, a more powerful evaluator LM than its predecessor that closely mirrors human and GPT-4 judgements. Moreover, it is capable of processing both direct assessment and pair-wise ranking formats grouped with a user-defined evaluation criteria. On four direct assessment benchmarks and four pairwise ranking benchmarks, Prometheus 2 scores the highest correlation and agreement with humans and proprietary LM judges among all tested open evaluator LMs. Our models, code, and data are all publicly available at https://github.com/prometheus-eval/prometheus-eval.

Evaluation of multilingual Large Language Models (LLMs) is challenging due to a variety of factors -- the lack of benchmarks with sufficient linguistic diversity, contamination of popular benchmarks into LLM pre-training data and the lack of local, cultural nuances in translated benchmarks. In this work, we study human and LLM-based evaluation in a multilingual, multi-cultural setting. We evaluate 30 models across 10 Indic languages by conducting 90K human evaluations and 30K LLM-based evaluations and find that models such as GPT-4o and Llama-3 70B consistently perform best for most Indic languages. We build leaderboards for two evaluation settings - pairwise comparison and direct assessment and analyse the agreement between humans and LLMs. We find that humans and LLMs agree fairly well in the pairwise setting but the agreement drops for direct assessment evaluation especially for languages such as Bengali and Odia. We also check for various biases in human and LLM-based evaluation and find evidence of self-bias in the GPT-based evaluator. Our work presents a significant step towards scaling up multilingual evaluation of LLMs.

While machine translation evaluation has been studied primarily for high-resource languages, there has been a recent interest in evaluation for low-resource languages due to the increasing availability of data and models. In this paper, we focus on a zero-shot evaluation setting focusing on low-resource Indian languages, namely Assamese, Kannada, Maithili, and Punjabi. We collect sufficient Multi-Dimensional Quality Metrics (MQM) and Direct Assessment (DA) annotations to create test sets and meta-evaluate a plethora of automatic evaluation metrics. We observe that even for learned metrics, which are known to exhibit zero-shot performance, the Kendall Tau and Pearson correlations with human annotations are only as high as 0.32 and 0.45. Synthetic data approaches show mixed results and overall do not help close the gap by much for these languages. This indicates that there is still a long way to go for low-resource evaluation.

This paper describes our submission of the WMT 2020 Shared Task on Sentence Level Direct Assessment, Quality Estimation (QE). In this study, we empirically reveal the mismatching issue when directly adopting BERTScore to QE. Specifically, there exist lots of mismatching errors between the source sentence and translated candidate sentence with token pairwise similarity. In response to this issue, we propose to expose explicit cross-lingual patterns, e.g. word alignments and generation score, to our proposed zero-shot models. Experiments show that our proposed QE model with explicit cross-lingual patterns could alleviate the mismatching issue, thereby improving the performance. Encouragingly, our zero-shot QE method could achieve comparable performance with supervised QE method, and even outperforms the supervised counterpart on 2 out of 6 directions. We expect our work could shed light on the zero-shot QE model improvement.

Machine Translation (MT) evaluation metrics assess translation quality automatically. Recently, researchers have employed MT metrics for various new use cases, such as data filtering and translation re-ranking. However, most MT metrics return assessments as scalar scores that are difficult to interpret, posing a challenge to making informed design choices. Moreover, MT metrics' capabilities have historically been evaluated using correlation with human judgment, which, despite its efficacy, falls short of providing intuitive insights into metric performance, especially in terms of new metric use cases. To address these issues, we introduce an interpretable evaluation framework for MT metrics. Within this framework, we evaluate metrics in two scenarios that serve as proxies for the data filtering and translation re-ranking use cases. Furthermore, by measuring the performance of MT metrics using Precision, Recall, and F-score, we offer clearer insights into their capabilities than correlation with human judgments. Finally, we raise concerns regarding the reliability of manually curated data following the Direct Assessments+Scalar Quality Metrics (DA+SQM) guidelines, reporting a notably low agreement with Multidimensional Quality Metrics (MQM) annotations.

We present COMET, a neural framework for training multilingual machine translation evaluation models which obtains new state-of-the-art levels of correlation with human judgements. Our framework leverages recent breakthroughs in cross-lingual pretrained language modeling resulting in highly multilingual and adaptable MT evaluation models that exploit information from both the source input and a target-language reference translation in order to more accurately predict MT quality. To showcase our framework, we train three models with different types of human judgements: Direct Assessments, Human-mediated Translation Edit Rate and Multidimensional Quality Metrics. Our models achieve new state-of-the-art performance on the WMT 2019 Metrics shared task and demonstrate robustness to high-performing systems.

With the primary focus on evaluating the effectiveness of large language models for automatic reference-less translation assessment, this work presents our experiments on mimicking human direct assessment to evaluate the quality of translations in English and Indian languages. We constructed a translation evaluation task where we performed zero-shot learning, in-context example-driven learning, and fine-tuning of large language models to provide a score out of 100, where 100 represents a perfect translation and 1 represents a poor translation. We compared the performance of our trained systems with existing methods such as COMET, BERT-Scorer, and LABSE, and found that the LLM-based evaluator (LLaMA-2-13B) achieves a comparable or higher overall correlation with human judgments for the considered Indian language pairs.

Despite the progress we have recorded in scaling multilingual machine translation (MT) models and evaluation data to several under-resourced African languages, it is difficult to measure accurately the progress we have made on these languages because evaluation is often performed on n-gram matching metrics like BLEU that often have worse correlation with human judgments. Embedding-based metrics such as COMET correlate better; however, lack of evaluation data with human ratings for under-resourced languages, complexity of annotation guidelines like Multidimensional Quality Metrics (MQM), and limited language coverage of multilingual encoders have hampered their applicability to African languages. In this paper, we address these challenges by creating high-quality human evaluation data with a simplified MQM guideline for error-span annotation and direct assessment (DA) scoring for 13 typologically diverse African languages. Furthermore, we develop AfriCOMET, a COMET evaluation metric for African languages by leveraging DA training data from high-resource languages and African-centric multilingual encoder (AfroXLM-Roberta) to create the state-of-the-art evaluation metric for African languages MT with respect to Spearman-rank correlation with human judgments (+0.406).

We present NUBIA, a methodology to build automatic evaluation metrics for text generation using only machine learning models as core components. A typical NUBIA model is composed of three modules: a neural feature extractor, an aggregator and a calibrator. We demonstrate an implementation of NUBIA which outperforms metrics currently used to evaluate machine translation, summaries and slightly exceeds/matches state of the art metrics on correlation with human judgement on the WMT segment-level Direct Assessment task, sentence-level ranking and image captioning evaluation. The model implemented is modular, explainable and set to continuously improve over time.

We present the contribution of the Unbabel team to the WMT 2020 Shared Task on Metrics. We intend to participate on the segment-level, document-level and system-level tracks on all language pairs, as well as the 'QE as a Metric' track. Accordingly, we illustrate results of our models in these tracks with reference to test sets from the previous year. Our submissions build upon the recently proposed COMET framework: We train several estimator models to regress on different human-generated quality scores and a novel ranking model trained on relative ranks obtained from Direct Assessments. We also propose a simple technique for converting segment-level predictions into a document-level score. Overall, our systems achieve strong results for all language pairs on previous test sets and in many cases set a new state-of-the-art.

As AI capabilities increasingly surpass human proficiency in complex tasks, current alignment techniques including SFT and RLHF face fundamental challenges in ensuring reliable oversight. These methods rely on direct human assessment and become untenable when AI outputs exceed human cognitive thresholds. In response to this challenge, we explore two hypotheses: (1) critique of critique can be easier than critique itself, extending the widely-accepted observation that verification is easier than generation to the critique domain, as critique itself is a specialized form of generation; (2) this difficulty relationship is recursively held, suggesting that when direct evaluation is infeasible, performing high-order critiques (e.g., critique of critique of critique) offers a more tractable supervision pathway. To examine these hypotheses, we perform Human-Human, Human-AI, and AI-AI experiments across multiple tasks. Our results demonstrate encouraging evidence supporting these hypotheses and suggest that recursive self-critiquing is a promising direction for scalable oversight.

The advancements of language language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about the true capabilities of such agents. In this work, we argue that for an agent to fully automate scientific discovery, it must be able to complete all essential tasks in the workflow. Thus, we call for rigorous assessment of agents on individual tasks in a scientific workflow before making bold claims on end-to-end automation. To this end, we present ScienceAgentBench, a new benchmark for evaluating language agents for data-driven scientific discovery. To ensure the scientific authenticity and real-world relevance of our benchmark, we extract 102 tasks from 44 peer-reviewed publications in four disciplines and engage nine subject matter experts to validate them. We unify the target output for every task to a self-contained Python program file and employ an array of evaluation metrics to examine the generated programs, execution results, and costs. Each task goes through multiple rounds of manual validation by annotators and subject matter experts to ensure its annotation quality and scientific plausibility. We also propose two effective strategies to mitigate data contamination concerns. Using our benchmark, we evaluate five open-weight and proprietary LLMs, each with three frameworks: direct prompting, OpenHands, and self-debug. Given three attempts for each task, the best-performing agent can only solve 32.4% of the tasks independently and 34.3% with expert-provided knowledge. These results underscore the limited capacities of current language agents in generating code for data-driven discovery, let alone end-to-end automation for scientific research.

In automated pronunciation assessment, recent emphasis progressively lies on evaluating multiple aspects to provide enriched feedback. However, acquiring multi-aspect-score labeled data for non-native language learners' speech poses challenges; moreover, it often leads to score-imbalanced distributions. In this paper, we propose two Acoustic Feature Mixup strategies, linearly and non-linearly interpolating with the in-batch averaged feature, to address data scarcity and score-label imbalances. Primarily using goodness-of-pronunciation as an acoustic feature, we tailor mixup designs to suit pronunciation assessment. Further, we integrate fine-grained error-rate features by comparing speech recognition results with the original answer phonemes, giving direct hints for mispronunciation. Effective mixing of the acoustic features notably enhances overall scoring performances on the speechocean762 dataset, and detailed analysis highlights our potential to predict unseen distortions.

This study explores the challenge of sentence-level AI-generated text detection within human-AI collaborative hybrid texts. Existing studies of AI-generated text detection for hybrid texts often rely on synthetic datasets. These typically involve hybrid texts with a limited number of boundaries. We contend that studies of detecting AI-generated content within hybrid texts should cover different types of hybrid texts generated in realistic settings to better inform real-world applications. Therefore, our study utilizes the CoAuthor dataset, which includes diverse, realistic hybrid texts generated through the collaboration between human writers and an intelligent writing system in multi-turn interactions. We adopt a two-step, segmentation-based pipeline: (i) detect segments within a given hybrid text where each segment contains sentences of consistent authorship, and (ii) classify the authorship of each identified segment. Our empirical findings highlight (1) detecting AI-generated sentences in hybrid texts is overall a challenging task because (1.1) human writers' selecting and even editing AI-generated sentences based on personal preferences adds difficulty in identifying the authorship of segments; (1.2) the frequent change of authorship between neighboring sentences within the hybrid text creates difficulties for segment detectors in identifying authorship-consistent segments; (1.3) the short length of text segments within hybrid texts provides limited stylistic cues for reliable authorship determination; (2) before embarking on the detection process, it is beneficial to assess the average length of segments within the hybrid text. This assessment aids in deciding whether (2.1) to employ a text segmentation-based strategy for hybrid texts with longer segments, or (2.2) to adopt a direct sentence-by-sentence classification strategy for those with shorter segments.

Large vision-language models (LVLMs) have recently witnessed rapid advancements, exhibiting a remarkable capacity for perceiving, understanding, and processing visual information by connecting visual receptor with large language models (LLMs). However, current assessments mainly focus on recognizing and reasoning abilities, lacking direct evaluation of conversational skills and neglecting visual storytelling abilities. In this paper, we propose an evaluation method that uses strong LLMs as judges to comprehensively evaluate the various abilities of LVLMs. Firstly, we construct a comprehensive visual dialogue dataset TouchStone, consisting of open-world images and questions, covering five major categories of abilities and 27 subtasks. This dataset not only covers fundamental recognition and comprehension but also extends to literary creation. Secondly, by integrating detailed image annotations we effectively transform the multimodal input content into a form understandable by LLMs. This enables us to employ advanced LLMs for directly evaluating the quality of the multimodal dialogue without requiring human intervention. Through validation, we demonstrate that powerful LVLMs, such as GPT-4, can effectively score dialogue quality by leveraging their textual capabilities alone, aligning with human preferences. We hope our work can serve as a touchstone for LVLMs' evaluation and pave the way for building stronger LVLMs. The evaluation code is available at https://github.com/OFA-Sys/TouchStone.

Modern reconstruction techniques can effectively model complex 3D scenes from sparse 2D views. However, automatically assessing the quality of novel views and identifying artifacts is challenging due to the lack of ground truth images and the limitations of no-reference image metrics in predicting detailed artifact maps. The absence of such quality metrics hinders accurate predictions of the quality of generated views and limits the adoption of post-processing techniques, such as inpainting, to enhance reconstruction quality. In this work, we propose a new no-reference metric, Puzzle Similarity, which is designed to localize artifacts in novel views. Our approach utilizes image patch statistics from the input views to establish a scene-specific distribution that is later used to identify poorly reconstructed regions in the novel views. We test and evaluate our method in the context of 3D reconstruction; to this end, we collected a novel dataset of human quality assessment in unseen reconstructed views. Through this dataset, we demonstrate that our method can not only successfully localize artifacts in novel views, correlating with human assessment, but do so without direct references. Surprisingly, our metric outperforms both no-reference metrics and popular full-reference image metrics. We can leverage our new metric to enhance applications like automatic image restoration, guided acquisition, or 3D reconstruction from sparse inputs.

Despite advancements in enhancing LLM safety against jailbreak attacks, evaluating LLM defenses remains a challenge, with current methods often lacking explainability and generalization to complex scenarios, leading to incomplete assessments (e.g., direct judgment without reasoning, low F1 score of GPT-4 in complex cases, bias in multilingual scenarios). To address this, we present JAILJUDGE, a comprehensive benchmark featuring diverse risk scenarios, including synthetic, adversarial, in-the-wild, and multilingual prompts, along with high-quality human-annotated datasets. The JAILJUDGE dataset includes over 35k+ instruction-tune data with reasoning explainability and JAILJUDGETEST, a 4.5k+ labeled set for risk scenarios, and a 6k+ multilingual set across ten languages. To enhance evaluation with explicit reasoning, we propose the JailJudge MultiAgent framework, which enables explainable, fine-grained scoring (1 to 10). This framework supports the construction of instruction-tuning ground truth and facilitates the development of JAILJUDGE Guard, an end-to-end judge model that provides reasoning and eliminates API costs. Additionally, we introduce JailBoost, an attacker-agnostic attack enhancer, and GuardShield, a moderation defense, both leveraging JAILJUDGE Guard. Our experiments demonstrate the state-of-the-art performance of JailJudge methods (JailJudge MultiAgent, JAILJUDGE Guard) across diverse models (e.g., GPT-4, Llama-Guard) and zero-shot scenarios. JailBoost and GuardShield significantly improve jailbreak attack and defense tasks under zero-shot settings, with JailBoost enhancing performance by 29.24% and GuardShield reducing defense ASR from 40.46% to 0.15%.

One of the most widely used methods to evaluate LLMs are Multiple Choice Question (MCQ) tests. MCQ benchmarks enable the testing of LLM knowledge on almost any topic at scale as the results can be processed automatically. To help the LLM answer, a few examples called few shots can be included in the prompt. Moreover, the LLM can be asked to answer the question directly with the selected option or to first provide the reasoning and then the selected answer, which is known as chain of thought. In addition to checking whether the selected answer is correct, the evaluation can look at the LLM-estimated probability of its response as an indication of the confidence of the LLM in the response. In this paper, we study how the LLM confidence in its answer depends on whether the model has been asked to answer directly or to provide the reasoning before answering. The results of the evaluation of questions on a wide range of topics in seven different models show that LLMs are more confident in their answers when they provide reasoning before the answer. This occurs regardless of whether the selected answer is correct. Our hypothesis is that this behavior is due to the reasoning that modifies the probability of the selected answer, as the LLM predicts the answer based on the input question and the reasoning that supports the selection made. Therefore, LLM estimated probabilities seem to have intrinsic limitations that should be understood in order to use them in evaluation procedures. Interestingly, the same behavior has been observed in humans, for whom explaining an answer increases confidence in its correctness.

This paper examines the zero-shot ability of Large Language Models (LLMs) to detect multiple-choice questions with no correct answer, a crucial aspect of educational assessment quality. We explore this ability not only as a measure of subject matter knowledge but also as an indicator of critical thinking within LLMs. Our experiments, utilizing a range of LLMs on diverse questions, highlight the significant performance gap between questions with a single correct answer and those without. Llama-3.1-405B stands out by successfully identifying the lack of a valid answer in many instances. These findings suggest that LLMs should prioritize critical thinking over blind instruction following and caution against their use in educational settings where questions with incorrect answers might lead to inaccurate evaluations. This research sets a benchmark for assessing critical thinking in LLMs and emphasizes the need for ongoing model alignment to ensure genuine user comprehension and assistance.

Text-based open-ended questions in academic formative and summative assessments help students become deep learners and prepare them to understand concepts for a subsequent conceptual assessment. However, grading text-based questions, especially in large courses, is tedious and time-consuming for instructors. Text processing models continue progressing with the rapid development of Artificial Intelligence (AI) tools and Natural Language Processing (NLP) algorithms. Especially after breakthroughs in Large Language Models (LLM), there is immense potential to automate rapid assessment and feedback of text-based responses in education. This systematic review adopts a scientific and reproducible literature search strategy based on the PRISMA process using explicit inclusion and exclusion criteria to study text-based automatic assessment systems in post-secondary education, screening 838 papers and synthesizing 93 studies. To understand how text-based automatic assessment systems have been developed and applied in education in recent years, three research questions are considered. All included studies are summarized and categorized according to a proposed comprehensive framework, including the input and output of the system, research motivation, and research outcomes, aiming to answer the research questions accordingly. Additionally, the typical studies of automated assessment systems, research methods, and application domains in these studies are investigated and summarized. This systematic review provides an overview of recent educational applications of text-based assessment systems for understanding the latest AI/NLP developments assisting in text-based assessments in higher education. Findings will particularly benefit researchers and educators incorporating LLMs such as ChatGPT into their educational activities.

Existing methods for controlling language models, such as RLHF and Constitutional AI, involve determining which LLM behaviors are desirable and training them into a language model. However, in many cases, it is desirable for LLMs to be controllable at inference time, so that they can be used in multiple contexts with diverse needs. We illustrate this with the Pink Elephant Problem: instructing an LLM to avoid discussing a certain entity (a ``Pink Elephant''), and instead discuss a preferred entity (``Grey Elephant''). We apply a novel simplification of Constitutional AI, Direct Principle Feedback, which skips the ranking of responses and uses DPO directly on critiques and revisions. Our results show that after DPF fine-tuning on our synthetic Pink Elephants dataset, our 13B fine-tuned LLaMA 2 model significantly outperforms Llama-2-13B-Chat and a prompted baseline, and performs as well as GPT-4 in on our curated test set assessing the Pink Elephant Problem.

The integration of artificial intelligence (AI) in educational measurement has revolutionized assessment methods, enabling automated scoring, rapid content analysis, and personalized feedback through machine learning and natural language processing. These advancements provide timely, consistent feedback and valuable insights into student performance, thereby enhancing the assessment experience. However, the deployment of AI in education also raises significant ethical concerns regarding validity, reliability, transparency, fairness, and equity. Issues such as algorithmic bias and the opacity of AI decision-making processes pose risks of perpetuating inequalities and affecting assessment outcomes. Responding to these concerns, various stakeholders, including educators, policymakers, and organizations, have developed guidelines to ensure ethical AI use in education. The National Council of Measurement in Education's Special Interest Group on AI in Measurement and Education (AIME) also focuses on establishing ethical standards and advancing research in this area. In this paper, a diverse group of AIME members examines the ethical implications of AI-powered tools in educational measurement, explores significant challenges such as automation bias and environmental impact, and proposes solutions to ensure AI's responsible and effective use in education.

Large language models (LLMs) have demonstrated their remarkable performance across various language understanding tasks. While emerging benchmarks have been proposed to evaluate LLMs in various domains such as mathematics and computer science, they merely measure the accuracy in terms of the final prediction on multi-choice questions. However, it remains insufficient to verify the essential understanding of LLMs given a chosen choice. To fill this gap, we present CLR-Bench to comprehensively evaluate the LLMs in complex college-level reasoning. Specifically, (i) we prioritize 16 challenging college disciplines in computer science and artificial intelligence. The dataset contains 5 types of questions, while each question is associated with detailed explanations from experts. (ii) To quantify a fair evaluation of LLMs' reasoning ability, we formalize the criteria with two novel metrics. QrightarrowA is utilized to measure the performance of direct answer prediction, and QrightarrowAR effectively considers the joint ability to answer the question and provide rationale simultaneously. Extensive experiments are conducted with 40 LLMs over 1,018 discipline-specific questions. The results demonstrate the key insights that LLMs, even the best closed-source LLM, i.e., GPT-4 turbo, tend to `guess' the college-level answers. It shows a dramatic decrease in accuracy from 63.31% QrightarrowA to 39.00% QrightarrowAR, indicating an unsatisfactory reasoning ability.

We present the ARC-DA dataset, a direct-answer ("open response", "freeform") version of the ARC (AI2 Reasoning Challenge) multiple-choice dataset. While ARC has been influential in the community, its multiple-choice format is unrepresentative of real-world questions, and multiple choice formats can be particularly susceptible to artifacts. The ARC-DA dataset addresses these concerns by converting questions to direct-answer format using a combination of crowdsourcing and expert review. The resulting dataset contains 2985 questions with a total of 8436 valid answers (questions typically have more than one valid answer). ARC-DA is one of the first DA datasets of natural questions that often require reasoning, and where appropriate question decompositions are not evident from the questions themselves. We describe the conversion approach taken, appropriate evaluation metrics, and several strong models. Although high, the best scores (81% GENIE, 61.4% F1, 63.2% ROUGE-L) still leave considerable room for improvement. In addition, the dataset provides a natural setting for new research on explanation, as many questions require reasoning to construct answers. We hope the dataset spurs further advances in complex question-answering by the community. ARC-DA is available at https://allenai.org/data/arc-da

It is desirable to coarsely classify short scientific texts, such as grant or publication abstracts, for strategic insight or research portfolio management. These texts efficiently transmit dense information to experts possessing a rich body of knowledge to aid interpretation. Yet this task is remarkably difficult to automate because of brevity and the absence of context. To address this gap, we have developed a novel approach to generate and appropriately assign coarse domain-specific labels. We show that a Large Language Model (LLM) can provide metadata essential to the task, in a process akin to the augmentation of supplemental knowledge representing human intuition, and propose a workflow. As a pilot study, we use a corpus of award abstracts from the National Aeronautics and Space Administration (NASA). We develop new assessment tools in concert with established performance metrics.

Numerous benchmarks have been established to assess the performance of foundation models on open-ended question answering, which serves as a comprehensive test of a model's ability to understand and generate language in a manner similar to humans. Most of these works focus on proposing new datasets, however, we see two main issues within previous benchmarking pipelines, namely testing leakage and evaluation automation. In this paper, we propose a novel benchmarking framework, Language-Model-as-an-Examiner, where the LM serves as a knowledgeable examiner that formulates questions based on its knowledge and evaluates responses in a reference-free manner. Our framework allows for effortless extensibility as various LMs can be adopted as the examiner, and the questions can be constantly updated given more diverse trigger topics. For a more comprehensive and equitable evaluation, we devise three strategies: (1) We instruct the LM examiner to generate questions across a multitude of domains to probe for a broad acquisition, and raise follow-up questions to engage in a more in-depth assessment. (2) Upon evaluation, the examiner combines both scoring and ranking measurements, providing a reliable result as it aligns closely with human annotations. (3) We additionally propose a decentralized Peer-examination method to address the biases in a single examiner. Our data and benchmarking results are available at: https://lmexam.com.

Researchers have argued that large language models (LLMs) exhibit high-quality writing capabilities from blogs to stories. However, evaluating objectively the creativity of a piece of writing is challenging. Inspired by the Torrance Test of Creative Thinking (TTCT), which measures creativity as a process, we use the Consensual Assessment Technique [3] and propose the Torrance Test of Creative Writing (TTCW) to evaluate creativity as a product. TTCW consists of 14 binary tests organized into the original dimensions of Fluency, Flexibility, Originality, and Elaboration. We recruit 10 creative writers and implement a human assessment of 48 stories written either by professional authors or LLMs using TTCW. Our analysis shows that LLM-generated stories pass 3-10X less TTCW tests than stories written by professionals. In addition, we explore the use of LLMs as assessors to automate the TTCW evaluation, revealing that none of the LLMs positively correlate with the expert assessments.

Recent developments in Generative Artificial Intelligence (GenAI) have created significant uncertainty in education, particularly in terms of assessment practices. Against this backdrop, we present an updated version of the AI Assessment Scale (AIAS), a framework with two fundamental purposes: to facilitate open dialogue between educators and students about appropriate GenAI use and to support educators in redesigning assessments in an era of expanding AI capabilities. Grounded in social constructivist principles and designed with assessment validity in mind, the AIAS provides a structured yet flexible approach that can be adapted across different educational contexts. Building on implementation feedback from global adoption across both the K-12 and higher education contexts, this revision represents a significant change from the original AIAS. Among these changes is a new visual guide that moves beyond the original traffic light system and utilises a neutral colour palette that avoids implied hierarchies between the levels. The scale maintains five distinct levels of GenAI integration in assessment, from "No AI" to "AI Exploration", but has been refined to better reflect rapidly advancing technological capabilities and emerging pedagogical needs. This paper presents the theoretical foundations of the revised framework, provides detailed implementation guidance through practical vignettes, and discusses its limitations and future directions. As GenAI capabilities continue to expand, particularly in multimodal content generation, the AIAS offers a starting point for reimagining assessment design in an era of disruptive technologies.

Despite growing interest in using large language models (LLMs) in healthcare, current explorations do not assess the real-world utility and safety of LLMs in clinical settings. Our objective was to determine whether two LLMs can serve information needs submitted by physicians as questions to an informatics consultation service in a safe and concordant manner. Sixty six questions from an informatics consult service were submitted to GPT-3.5 and GPT-4 via simple prompts. 12 physicians assessed the LLM responses' possibility of patient harm and concordance with existing reports from an informatics consultation service. Physician assessments were summarized based on majority vote. For no questions did a majority of physicians deem either LLM response as harmful. For GPT-3.5, responses to 8 questions were concordant with the informatics consult report, 20 discordant, and 9 were unable to be assessed. There were 29 responses with no majority on "Agree", "Disagree", and "Unable to assess". For GPT-4, responses to 13 questions were concordant, 15 discordant, and 3 were unable to be assessed. There were 35 responses with no majority. Responses from both LLMs were largely devoid of overt harm, but less than 20% of the responses agreed with an answer from an informatics consultation service, responses contained hallucinated references, and physicians were divided on what constitutes harm. These results suggest that while general purpose LLMs are able to provide safe and credible responses, they often do not meet the specific information need of a given question. A definitive evaluation of the usefulness of LLMs in healthcare settings will likely require additional research on prompt engineering, calibration, and custom-tailoring of general purpose models.

Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data (usually one chosen and rejected response pair per user prompt) to align LLMs to human preferences. In practice, multiple responses can exist for a given prompt with varying quality relative to each other. With availability of such quality ratings for multiple responses, we propose utilizing these responses to create multiple preference pairs for a given prompt. Our work focuses on systematically using the constructed multiple preference pair in DPO training via curriculum learning methodology. In particular, we order these multiple pairs of preference data from easy to hard (emulating curriculum training) according to various criteria. We show detailed comparisons of our proposed approach to the standard single-pair DPO setting. Our method, which we call Curry-DPO consistently shows increased performance gains on MTbench, Vicuna, WizardLM, and the UltraFeedback test set, highlighting its effectiveness. More specifically, Curry-DPO achieves a score of 7.43 on MT-bench with Zephy-7B model outperforming majority of existing LLMs with similar parameter size. Curry-DPO also achieves the highest adjusted win rates on Vicuna, WizardLM, and UltraFeedback test datasets (90.7%, 87.1%, and 87.9% respectively) in our experiments, with notable gains of upto 7.5% when compared to standard DPO technique.

This study investigates GPT-4's assessment of its performance in healthcare applications. A simple prompting technique was used to prompt the LLM with questions taken from the United States Medical Licensing Examination (USMLE) questionnaire and it was tasked to evaluate its confidence score before posing the question and after asking the question. The questionnaire was categorized into two groups-questions with feedback (WF) and questions with no feedback(NF) post-question. The model was asked to provide absolute and relative confidence scores before and after each question. The experimental findings were analyzed using statistical tools to study the variability of confidence in WF and NF groups. Additionally, a sequential analysis was conducted to observe the performance variation for the WF and NF groups. Results indicate that feedback influences relative confidence but doesn't consistently increase or decrease it. Understanding the performance of LLM is paramount in exploring its utility in sensitive areas like healthcare. This study contributes to the ongoing discourse on the reliability of AI, particularly of LLMs like GPT-4, within healthcare, offering insights into how feedback mechanisms might be optimized to enhance AI-assisted medical education and decision support.

Recent advances in large language models (LLMs) have led to the development of various evaluation benchmarks. These benchmarks typically rely on a single instruction template for evaluating all LLMs on a specific task. In this paper, we comprehensively analyze the brittleness of results obtained via single-prompt evaluations across 6.5M instances, involving 20 different LLMs and 39 tasks from 3 benchmarks. To improve robustness of the analysis, we propose to evaluate LLMs with a set of diverse prompts instead. We discuss tailored evaluation metrics for specific use cases (e.g., LLM developers vs. developers interested in a specific downstream task), ensuring a more reliable and meaningful assessment of LLM capabilities. We then implement these criteria and conduct evaluations of multiple models, providing insights into the true strengths and limitations of current LLMs.

Scalable oversight protocols aim to enable humans to accurately supervise superhuman AI. In this paper we study debate, where two AI's compete to convince a judge; consultancy, where a single AI tries to convince a judge that asks questions; and compare to a baseline of direct question-answering, where the judge just answers outright without the AI. We use large language models (LLMs) as both AI agents and as stand-ins for human judges, taking the judge models to be weaker than agent models. We benchmark on a diverse range of asymmetries between judges and agents, extending previous work on a single extractive QA task with information asymmetry, to also include mathematics, coding, logic and multimodal reasoning asymmetries. We find that debate outperforms consultancy across all tasks when the consultant is randomly assigned to argue for the correct/incorrect answer. Comparing debate to direct question answering, the results depend on the type of task: in extractive QA tasks with information asymmetry debate outperforms direct question answering, but in other tasks without information asymmetry the results are mixed. Previous work assigned debaters/consultants an answer to argue for. When we allow them to instead choose which answer to argue for, we find judges are less frequently convinced by the wrong answer in debate than in consultancy. Further, we find that stronger debater models increase judge accuracy, though more modestly than in previous studies.

An accurate differential diagnosis (DDx) is a cornerstone of medical care, often reached through an iterative process of interpretation that combines clinical history, physical examination, investigations and procedures. Interactive interfaces powered by Large Language Models (LLMs) present new opportunities to both assist and automate aspects of this process. In this study, we introduce an LLM optimized for diagnostic reasoning, and evaluate its ability to generate a DDx alone or as an aid to clinicians. 20 clinicians evaluated 302 challenging, real-world medical cases sourced from the New England Journal of Medicine (NEJM) case reports. Each case report was read by two clinicians, who were randomized to one of two assistive conditions: either assistance from search engines and standard medical resources, or LLM assistance in addition to these tools. All clinicians provided a baseline, unassisted DDx prior to using the respective assistive tools. Our LLM for DDx exhibited standalone performance that exceeded that of unassisted clinicians (top-10 accuracy 59.1% vs 33.6%, [p = 0.04]). Comparing the two assisted study arms, the DDx quality score was higher for clinicians assisted by our LLM (top-10 accuracy 51.7%) compared to clinicians without its assistance (36.1%) (McNemar's Test: 45.7, p < 0.01) and clinicians with search (44.4%) (4.75, p = 0.03). Further, clinicians assisted by our LLM arrived at more comprehensive differential lists than those without its assistance. Our study suggests that our LLM for DDx has potential to improve clinicians' diagnostic reasoning and accuracy in challenging cases, meriting further real-world evaluation for its ability to empower physicians and widen patients' access to specialist-level expertise.

One of the most concrete measures to take towards meaningful AI accountability is to consequentially assess and report the systems' performance and impact. However, the practical nature of the "AI audit" ecosystem is muddled and imprecise, making it difficult to work through various concepts and map out the stakeholders involved in the practice. First, we taxonomize current AI audit practices as completed by regulators, law firms, civil society, journalism, academia, consulting agencies. Next, we assess the impact of audits done by stakeholders within each domain. We find that only a subset of AI audit studies translate to desired accountability outcomes. We thus assess and isolate practices necessary for effective AI audit results, articulating the observed connections between AI audit design, methodology and institutional context on its effectiveness as a meaningful mechanism for accountability.

Multiple choice question answering (MCQA) is popular for LLM evaluation due to its simplicity and human-like testing, but we argue for its reform. We first reveal flaws in MCQA's format, as it struggles to: 1) test generation/subjectivity; 2) match LLM use cases; and 3) fully test knowledge. We instead advocate for generative formats based on human testing-where LLMs construct and explain answers-better capturing user needs and knowledge while remaining easy to score. We then show even when MCQA is a useful format, its datasets suffer from: leakage; unanswerability; shortcuts; and saturation. In each issue, we give fixes from education, like rubrics to guide MCQ writing; scoring methods to bridle guessing; and Item Response Theory to build harder MCQs. Lastly, we discuss LLM errors in MCQA-robustness, biases, and unfaithful explanations-showing how our prior solutions better measure or address these issues. While we do not need to desert MCQA, we encourage more efforts in refining the task based on educational testing, advancing evaluations.

Multiple-choice question answering (MCQA) is often used to evaluate large language models (LLMs). To see if MCQA assesses LLMs as intended, we probe if LLMs can perform MCQA with choices-only prompts, where models must select the correct answer only from the choices. In three MCQA datasets and four LLMs, this prompt bests a majority baseline in 11/12 cases, with up to 0.33 accuracy gain. To help explain this behavior, we conduct an in-depth, black-box analysis on memorization, choice dynamics, and question inference. Our key findings are threefold. First, we find no evidence that the choices-only accuracy stems from memorization alone. Second, priors over individual choices do not fully explain choices-only accuracy, hinting that LLMs use the group dynamics of choices. Third, LLMs have some ability to infer a relevant question from choices, and surprisingly can sometimes even match the original question. We hope to motivate the use of stronger baselines in MCQA benchmarks, the design of robust MCQA datasets, and further efforts to explain LLM decision-making.

As Large Language Models (LLMs) become more pervasive across various users and scenarios, identifying potential issues when using these models becomes essential. Examples of such issues include: bias, inconsistencies, and hallucination. Although auditing the LLM for these problems is often warranted, such a process is neither easy nor accessible for most. An effective method is to probe the LLM using different versions of the same question. This could expose inconsistencies in its knowledge or operation, indicating potential for bias or hallucination. However, to operationalize this auditing method at scale, we need an approach to create those probes reliably and automatically. In this paper we propose the LLMAuditor framework which is an automatic, and scalable solution, where one uses a different LLM along with human-in-the-loop (HIL). This approach offers verifiability and transparency, while avoiding circular reliance on the same LLM, and increasing scientific rigor and generalizability. Specifically, LLMAuditor includes two phases of verification using humans: standardized evaluation criteria to verify responses, and a structured prompt template to generate desired probes. A case study using questions from the TruthfulQA dataset demonstrates that we can generate a reliable set of probes from one LLM that can be used to audit inconsistencies in a different LLM. This process is enhanced by our structured prompt template with HIL, which not only boosts the reliability of our approach in auditing but also yields the delivery of less hallucinated results. The novelty of our research stems from the development of a comprehensive, general-purpose framework that includes a HIL verified prompt template for auditing responses generated by LLMs.

The impressive performance of large language models (LLMs) has attracted considerable attention from the academic and industrial communities. Besides how to construct and train LLMs, how to effectively evaluate and compare the capacity of LLMs has also been well recognized as an important yet difficult problem. Existing paradigms rely on either human annotators or model-based evaluators to evaluate the performance of LLMs on different tasks. However, these paradigms often suffer from high cost, low generalizability, and inherited biases in practice, which make them incapable of supporting the sustainable development of LLMs in long term. In order to address these issues, inspired by the peer review systems widely used in academic publication process, we propose a novel framework that can automatically evaluate LLMs through a peer-review process. Specifically, for the evaluation of a specific task, we first construct a small qualification exam to select "reviewers" from a couple of powerful LLMs. Then, to actually evaluate the "submissions" written by different candidate LLMs, i.e., the evaluatees, we use the reviewer LLMs to rate or compare the submissions. The final ranking of evaluatee LLMs is generated based on the results provided by all reviewers. We conducted extensive experiments on text summarization tasks with eleven LLMs including GPT-4. The results demonstrate the existence of biasness when evaluating using a single LLM. Also, our PRE model outperforms all the baselines, illustrating the effectiveness of the peer review mechanism.

Reinforcement Learning From Human Feedback (RLHF) has been a critical to the success of the latest generation of generative AI models. In response to the complex nature of the classical RLHF pipeline, direct alignment algorithms such as Direct Preference Optimization (DPO) have emerged as an alternative approach. Although DPO solves the same objective as the standard RLHF setup, there is a mismatch between the two approaches. Standard RLHF deploys reinforcement learning in a specific token-level MDP, while DPO is derived as a bandit problem in which the whole response of the model is treated as a single arm. In this work we rectify this difference, first we theoretically show that we can derive DPO in the token-level MDP as a general inverse Q-learning algorithm, which satisfies the Bellman equation. Using our theoretical results, we provide three concrete empirical insights. First, we show that because of its token level interpretation, DPO is able to perform some type of credit assignment. Next, we prove that under the token level formulation, classical search-based algorithms, such as MCTS, which have recently been applied to the language generation space, are equivalent to likelihood-based search on a DPO policy. Empirically we show that a simple beam search yields meaningful improvement over the base DPO policy. Finally, we show how the choice of reference policy causes implicit rewards to decline during training. We conclude by discussing applications of our work, including information elicitation in multi-tun dialogue, reasoning, agentic applications and end-to-end training of multi-model systems.

Despite their sophisticated capabilities, large language models (LLMs) encounter a major hurdle in effective assessment. This paper first revisits the prevalent evaluation method-multiple choice question answering (MCQA), which allows for straightforward accuracy measurement. Through a comprehensive evaluation of 24 models across 11 benchmarks, we highlight several potential drawbacks of MCQA, for instance, the inconsistency between the MCQA evaluation and the generation of open-ended responses in practical scenarios. In response, we introduce an RWQ-Elo rating system, engaging 24 LLMs such as GPT-4, GPT-3.5, Google-Gemini-Pro and LLaMA-1/-2, in a two-player competitive format, with GPT-4 serving as the judge. Each LLM receives an Elo rating thereafter. This system is designed to mirror real-world usage, and for this purpose, we have compiled a new benchmark called ``Real-world questions'' (RWQ), comprising 20,772 authentic user inquiries. Additionally, we thoroughly analyze the characteristics of our system and compare it with prior leaderboards like AlpacaEval and MT-Bench. Our analysis reveals the stability of our RWQ-Elo system, the feasibility of registering new models, and its potential to reshape LLM leaderboards.

Direct alignment from preferences (DAP) methods, such as DPO, have recently emerged as efficient alternatives to reinforcement learning from human feedback (RLHF), that do not require a separate reward model. However, the preference datasets used in DAP methods are usually collected ahead of training and never updated, thus the feedback is purely offline. Moreover, responses in these datasets are often sampled from a language model distinct from the one being aligned, and since the model evolves over training, the alignment phase is inevitably off-policy. In this study, we posit that online feedback is key and improves DAP methods. Our method, online AI feedback (OAIF), uses an LLM as annotator: on each training iteration, we sample two responses from the current model and prompt the LLM annotator to choose which one is preferred, thus providing online feedback. Despite its simplicity, we demonstrate via human evaluation in several tasks that OAIF outperforms both offline DAP and RLHF methods. We further show that the feedback leveraged in OAIF is easily controllable, via instruction prompts to the LLM annotator.

We introduce WiCkeD, a simple method to increase the complexity of existing multiple-choice benchmarks by randomly replacing a choice with "None of the above", a method often used in educational tests. We show that WiCkeD can be automatically applied to any existing benchmark, making it more challenging. We apply WiCkeD to 6 popular benchmarks and use it to evaluate 18 open-weight LLMs. The performance of the models drops 12.1 points on average with respect to the original versions of the datasets. When using chain-of-thought on 3 MMLU datasets, the performance drop for the WiCkeD variant is similar to the one observed when using the LLMs directly, showing that WiCkeD is also challenging for models with enhanced reasoning abilities. WiCkeD also uncovers that some models are more sensitive to the extra reasoning required, providing additional information with respect to the original benchmarks. We relase our code and data at https://github.com/ahmedselhady/wicked-benchmarks.

As large language models (LLM) evolve in their capabilities, various recent studies have tried to quantify their behavior using psychological tools created to study human behavior. One such example is the measurement of "personality" of LLMs using self-assessment personality tests developed to measure human personality. Yet almost none of these works verify the applicability of these tests on LLMs. In this paper, we analyze the reliability of LLM personality scores obtained from self-assessment personality tests using two simple experiments. We first introduce the property of prompt sensitivity, where three semantically equivalent prompts representing three intuitive ways of administering self-assessment tests on LLMs are used to measure the personality of the same LLM. We find that all three prompts lead to very different personality scores, a difference that is statistically significant for all traits in a large majority of scenarios. We then introduce the property of option-order symmetry for personality measurement of LLMs. Since most of the self-assessment tests exist in the form of multiple choice question (MCQ) questions, we argue that the scores should also be robust to not just the prompt template but also the order in which the options are presented. This test unsurprisingly reveals that the self-assessment test scores are not robust to the order of the options. These simple tests, done on ChatGPT and three Llama2 models of different sizes, show that self-assessment personality tests created for humans are unreliable measures of personality in LLMs.

Large Language Models, such as Generative Pre-trained Transformer 3 (aka. GPT-3), have been developed to understand language through the analysis of extensive text data, allowing them to identify patterns and connections between words. While LLMs have demonstrated impressive performance across various text-related tasks, they encounter challenges in tasks associated with reasoning. To address this challenge, Chain of Thought(CoT) prompting method has been proposed as a means to enhance LLMs' proficiency in complex reasoning tasks like solving math word problems and answering questions based on logical argumentative reasoning. The primary aim of this research is to assess how well four language models can grade reflective essays of third-year medical students. The assessment will specifically target the evaluation of critical thinking skills using CoT prompting. The research will provide the following contributions; to introduce and educate on the process of instructing models to evaluate reflective essays from a dataset they have not been previously trained on; to illustrate the use of CoT prompting as an instructional approach for training large models to carry out particular tasks. Our results suggest that among all the models, Llama-7b performs the least effectively, displaying the highest mean squared error. Conversely, ChatGPT emerges as the superior model, boasting a higher Cohen kappa score value of 0.53. Lastly, it's important to note that the selected models do prioritise user privacy by allowing users to delete their own conducted conversations.

Developers and quality assurance testers often rely on manual testing to test accessibility features throughout the product lifecycle. Unfortunately, manual testing can be tedious, often has an overwhelming scope, and can be difficult to schedule amongst other development milestones. Recently, Large Language Models (LLMs) have been used for a variety of tasks including automation of UIs, however to our knowledge no one has yet explored their use in controlling assistive technologies for the purposes of supporting accessibility testing. In this paper, we explore the requirements of a natural language based accessibility testing workflow, starting with a formative study. From this we build a system that takes as input a manual accessibility test (e.g., ``Search for a show in VoiceOver'') and uses an LLM combined with pixel-based UI Understanding models to execute the test and produce a chaptered, navigable video. In each video, to help QA testers we apply heuristics to detect and flag accessibility issues (e.g., Text size not increasing with Large Text enabled, VoiceOver navigation loops). We evaluate this system through a 10 participant user study with accessibility QA professionals who indicated that the tool would be very useful in their current work and performed tests similarly to how they would manually test the features. The study also reveals insights for future work on using LLMs for accessibility testing.

ARC Challenge appears more difficult than ARC Easy for modern LLMs primarily due to an evaluation setup that prevents direct comparison of answer choices rather than inherent complexity. Although some researchers have quietly shifted to a more appropriate scheme over the last year, the implications of this change have yet to be widely acknowledged. We highlight this overlooked shift, show how similar evaluation practices falsely imply reasoning deficits in other benchmarks, and demonstrate that fairer methods dramatically reduce performance gaps (e.g. on SIQA) and even yield superhuman results (OpenBookQA). In doing so, we reveal how evaluation shapes perceived difficulty and offer guidelines to ensure that multiple-choice evaluations accurately reflect actual model capabilities.

We present SimpleQA, a benchmark that evaluates the ability of language models to answer short, fact-seeking questions. We prioritized two properties in designing this eval. First, SimpleQA is challenging, as it is adversarially collected against GPT-4 responses. Second, responses are easy to grade, because questions are created such that there exists only a single, indisputable answer. Each answer in SimpleQA is graded as either correct, incorrect, or not attempted. A model with ideal behavior would get as many questions correct as possible while not attempting the questions for which it is not confident it knows the correct answer. SimpleQA is a simple, targeted evaluation for whether models "know what they know," and our hope is that this benchmark will remain relevant for the next few generations of frontier models. SimpleQA can be found at https://github.com/openai/simple-evals.

Large Language Models (LLMs) are often described as being instances of foundation models - that is, models that transfer strongly across various tasks and conditions in few-show or zero-shot manner, while exhibiting scaling laws that predict function improvement when increasing the pre-training scale. These claims of excelling in different functions and tasks rely on measurements taken across various sets of standardized benchmarks showing high scores for such models. We demonstrate here a dramatic breakdown of function and reasoning capabilities of state-of-the-art models trained at the largest available scales which claim strong function, using a simple, short, conventional common sense problem formulated in concise natural language, easily solvable by humans. The breakdown is dramatic, as models also express strong overconfidence in their wrong solutions, while providing often non-sensical "reasoning"-like explanations akin to confabulations to justify and backup the validity of their clearly failed responses, making them sound plausible. Various standard interventions in an attempt to get the right solution, like various type of enhanced prompting, or urging the models to reconsider the wrong solutions again by multi step re-evaluation, fail. We take these initial observations to the scientific and technological community to stimulate urgent re-assessment of the claimed capabilities of current generation of LLMs, Such re-assessment also requires common action to create standardized benchmarks that would allow proper detection of such basic reasoning deficits that obviously manage to remain undiscovered by current state-of-the-art evaluation procedures and benchmarks. Code for reproducing experiments in the paper and raw experiments data can be found at https://github.com/LAION-AI/AIW

In the field of psychology, traditional assessment methods, such as standardized scales, are frequently critiqued for their static nature, lack of personalization, and reduced participant engagement, while comprehensive counseling evaluations are often inaccessible. The complexity of quantifying psychological traits further limits these methods. Despite advances with large language models (LLMs), many still depend on single-round Question-and-Answer interactions. To bridge this gap, we introduce PsyDI, a personalized and progressively in-depth chatbot designed for psychological measurements, exemplified by its application in the Myers-Briggs Type Indicator (MBTI) framework. PsyDI leverages user-related multi-modal information and engages in customized, multi-turn interactions to provide personalized, easily accessible measurements, while ensuring precise MBTI type determination. To address the challenge of unquantifiable psychological traits, we introduce a novel training paradigm that involves learning the ranking of proxy variables associated with these traits, culminating in a robust score model for MBTI measurements. The score model enables PsyDI to conduct comprehensive and precise measurements through multi-turn interactions within a unified estimation context. Through various experiments, we validate the efficacy of both the score model and the PsyDI pipeline, demonstrating its potential to serve as a general framework for psychological measurements. Furthermore, the online deployment of PsyDI has garnered substantial user engagement, with over 3,000 visits, resulting in the collection of numerous multi-turn dialogues annotated with MBTI types, which facilitates further research.

Large Language Models (LLMs) have acquired ubiquitous attention for their performances across diverse domains. Our study here searches through LLMs' cognitive abilities and confidence dynamics. We dive deep into understanding the alignment between their self-assessed confidence and actual performance. We exploit these models with diverse sets of questionnaires and real-world scenarios and extract how LLMs exhibit confidence in their responses. Our findings reveal intriguing instances where models demonstrate high confidence even when they answer incorrectly. This is reminiscent of the Dunning-Kruger effect observed in human psychology. In contrast, there are cases where models exhibit low confidence with correct answers revealing potential underestimation biases. Our results underscore the need for a deeper understanding of their cognitive processes. By examining the nuances of LLMs' self-assessment mechanism, this investigation provides noteworthy revelations that serve to advance the functionalities and broaden the potential applications of these formidable language models.

Direct Alignment Algorithms (DAAs) simplify language model alignment by replacing reinforcement learning (RL) and reward modeling (RM) in Reinforcement Learning from Human Feedback (RLHF) with direct policy optimization. DAAs can be classified by their ranking losses (pairwise vs. pointwise), by the rewards used in those losses (e.g., likelihood ratios of policy and reference policy, or odds ratios), or by whether a Supervised Fine-Tuning (SFT) phase is required (two-stage vs. one-stage). We first show that one-stage methods underperform two-stage methods. To address this, we incorporate an explicit SFT phase and introduce the beta parameter, controlling the strength of preference optimization, into single-stage ORPO and ASFT. These modifications improve their performance in Alpaca Eval 2 by +3.46 (ORPO) and +8.27 (ASFT), matching two-stage methods like DPO. Further analysis reveals that the key factor is whether the approach uses pairwise or pointwise objectives, rather than the specific implicit reward or loss function. These results highlight the importance of careful evaluation to avoid premature claims of performance gains or overall superiority in alignment algorithms.

This study evaluates the performance of OpenAI's o1-preview model in higher-order cognitive domains, including critical thinking, systematic thinking, computational thinking, data literacy, creative thinking, logical reasoning, and scientific reasoning. Using established benchmarks, we compared the o1-preview models's performance to human participants from diverse educational levels. o1-preview achieved a mean score of 24.33 on the Ennis-Weir Critical Thinking Essay Test (EWCTET), surpassing undergraduate (13.8) and postgraduate (18.39) participants (z = 1.60 and 0.90, respectively). In systematic thinking, it scored 46.1, SD = 4.12 on the Lake Urmia Vignette, significantly outperforming the human mean (20.08, SD = 8.13, z = 3.20). For data literacy, o1-preview scored 8.60, SD = 0.70 on Merk et al.'s "Use Data" dimension, compared to the human post-test mean of 4.17, SD = 2.02 (z = 2.19). On creative thinking tasks, the model achieved originality scores of 2.98, SD = 0.73, higher than the human mean of 1.74 (z = 0.71). In logical reasoning (LogiQA), it outperformed humans with average 90%, SD = 10% accuracy versus 86%, SD = 6.5% (z = 0.62). For scientific reasoning, it achieved near-perfect performance (mean = 0.99, SD = 0.12) on the TOSLS,, exceeding the highest human scores of 0.85, SD = 0.13 (z = 1.78). While o1-preview excelled in structured tasks, it showed limitations in problem-solving and adaptive reasoning. These results demonstrate the potential of AI to complement education in structured assessments but highlight the need for ethical oversight and refinement for broader applications.

Ensuring the accuracy of responses provided by large language models (LLMs) is crucial, particularly in clinical settings where incorrect information may directly impact patient health. To address this challenge, we construct K-QA, a dataset containing 1,212 patient questions originating from real-world conversations held on K Health (an AI-driven clinical platform). We employ a panel of in-house physicians to answer and manually decompose a subset of K-QA into self-contained statements. Additionally, we formulate two NLI-based evaluation metrics approximating recall and precision: (1) comprehensiveness, measuring the percentage of essential clinical information in the generated answer and (2) hallucination rate, measuring the number of statements from the physician-curated response contradicted by the LLM answer. Finally, we use K-QA along with these metrics to evaluate several state-of-the-art models, as well as the effect of in-context learning and medically-oriented augmented retrieval schemes developed by the authors. Our findings indicate that in-context learning improves the comprehensiveness of the models, and augmented retrieval is effective in reducing hallucinations. We make K-QA available to to the community to spur research into medically accurate NLP applications.

Timely, personalized feedback is essential for students learning programming, especially as class sizes expand. LLM-based tools like ChatGPT offer instant support, but reveal direct answers with code, which may hinder deep conceptual engagement. We developed CodeAid, an LLM-based programming assistant delivering helpful, technically correct responses, without revealing code solutions. For example, CodeAid can answer conceptual questions, generate pseudo-code with line-by-line explanations, and annotate student's incorrect code with fix suggestions. We deployed CodeAid in a programming class of 700 students for a 12-week semester. A thematic analysis of 8,000 usages of CodeAid was performed, further enriched by weekly surveys, and 22 student interviews. We then interviewed eight programming educators to gain further insights on CodeAid. Findings revealed students primarily used CodeAid for conceptual understanding and debugging, although a minority tried to obtain direct code. Educators appreciated CodeAid's educational approach, and expressed concerns about occasional incorrect feedback and students defaulting to ChatGPT.

Detecting stereotypes and biases in Large Language Models (LLMs) can enhance fairness and reduce adverse impacts on individuals or groups when these LLMs are applied. However, the majority of existing methods focus on measuring the model's preference towards sentences containing biases and stereotypes within datasets, which lacks interpretability and cannot detect implicit biases and stereotypes in the real world. To address this gap, this paper introduces a four-stage framework to directly evaluate stereotypes and biases in the generated content of LLMs, including direct inquiry testing, serial or adapted story testing, implicit association testing, and unknown situation testing. Additionally, the paper proposes multi-dimensional evaluation metrics and explainable zero-shot prompts for automated evaluation. Using the education sector as a case study, we constructed the Edu-FairBench based on the four-stage framework, which encompasses 12,632 open-ended questions covering nine sensitive factors and 26 educational scenarios. Experimental results reveal varying degrees of stereotypes and biases in five LLMs evaluated on Edu-FairBench. Moreover, the results of our proposed automated evaluation method have shown a high correlation with human annotations.

Skills play a central role in the job market and many human resources (HR) processes. In the wake of other digital experiences, today's online job market has candidates expecting to see the right opportunities based on their skill set. Similarly, enterprises increasingly need to use data to guarantee that the skills within their workforce remain future-proof. However, structured information about skills is often missing, and processes building on self- or manager-assessment have shown to struggle with issues around adoption, completeness, and freshness of the resulting data. Extracting skills is a highly challenging task, given the many thousands of possible skill labels mentioned either explicitly or merely described implicitly and the lack of finely annotated training corpora. Previous work on skill extraction overly simplifies the task to an explicit entity detection task or builds on manually annotated training data that would be infeasible if applied to a complete vocabulary of skills. We propose an end-to-end system for skill extraction, based on distant supervision through literal matching. We propose and evaluate several negative sampling strategies, tuned on a small validation dataset, to improve the generalization of skill extraction towards implicitly mentioned skills, despite the lack of such implicit skills in the distantly supervised data. We observe that using the ESCO taxonomy to select negative examples from related skills yields the biggest improvements, and combining three different strategies in one model further increases the performance, up to 8 percentage points in RP@5. We introduce a manually annotated evaluation benchmark for skill extraction based on the ESCO taxonomy, on which we validate our models. We release the benchmark dataset for research purposes to stimulate further research on the task.

Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which datasets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark's measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. ECBD specifies the role each module plays in helping practitioners collect evidence about capabilities of interest. Specifically, each module requires benchmark designers to describe, justify, and support benchmark design choices -- e.g., clearly specifying the capabilities the benchmark aims to measure or how evidence about those capabilities is collected from model responses. To demonstrate the use of ECBD, we conduct case studies with three benchmarks: BoolQ, SuperGLUE, and HELM. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks' measurements.

State-of-the-art language models (LMs) are notoriously susceptible to generating hallucinated information. Such inaccurate outputs not only undermine the reliability of these models but also limit their use and raise serious concerns about misinformation and propaganda. In this work, we focus on hallucinated book and article references and present them as the "model organism" of language model hallucination research, due to their frequent and easy-to-discern nature. We posit that if a language model cites a particular reference in its output, then it should ideally possess sufficient information about its authors and content, among other relevant details. Using this basic insight, we illustrate that one can identify hallucinated references without ever consulting any external resources, by asking a set of direct or indirect queries to the language model about the references. These queries can be considered as "consistency checks." Our findings highlight that while LMs, including GPT-4, often produce inconsistent author lists for hallucinated references, they also often accurately recall the authors of real references. In this sense, the LM can be said to "know" when it is hallucinating references. Furthermore, these findings show how hallucinated references can be dissected to shed light on their nature. Replication code and results can be found at https://github.com/microsoft/hallucinated-references.

When asked, current large language models (LLMs) like ChatGPT claim that they can assist us with relevance judgments. Many researchers think this would not lead to credible IR research. In this perspective paper, we discuss possible ways for LLMs to assist human experts along with concerns and issues that arise. We devise a human-machine collaboration spectrum that allows categorizing different relevance judgment strategies, based on how much the human relies on the machine. For the extreme point of "fully automated assessment", we further include a pilot experiment on whether LLM-based relevance judgments correlate with judgments from trained human assessors. We conclude the paper by providing two opposing perspectives - for and against the use of LLMs for automatic relevance judgments - and a compromise perspective, informed by our analyses of the literature, our preliminary experimental evidence, and our experience as IR researchers. We hope to start a constructive discussion within the community to avoid a stale-mate during review, where work is dammed if is uses LLMs for evaluation and dammed if it doesn't.

Large language models (LLMs) have made significant advancements in various natural language processing tasks, including question answering (QA) tasks. While incorporating new information with the retrieval of relevant passages is a promising way to improve QA with LLMs, the existing methods often require additional fine-tuning which becomes infeasible with recent LLMs. Augmenting retrieved passages via prompting has the potential to address this limitation, but this direction has been limitedly explored. To this end, we design a simple yet effective framework to enhance open-domain QA (ODQA) with LLMs, based on the summarized retrieval (SuRe). SuRe helps LLMs predict more accurate answers for a given question, which are well-supported by the summarized retrieval that could be viewed as an explicit rationale extracted from the retrieved passages. Specifically, SuRe first constructs summaries of the retrieved passages for each of the multiple answer candidates. Then, SuRe confirms the most plausible answer from the candidate set by evaluating the validity and ranking of the generated summaries. Experimental results on diverse ODQA benchmarks demonstrate the superiority of SuRe, with improvements of up to 4.6% in exact match (EM) and 4.0% in F1 score over standard prompting approaches. SuRe also can be integrated with a broad range of retrieval methods and LLMs. Finally, the generated summaries from SuRe show additional advantages to measure the importance of retrieved passages and serve as more preferred rationales by models and humans.

Online medical consultation (OMC) restricts doctors to gathering patient information solely through inquiries, making the already complex sequential decision-making process of diagnosis even more challenging. Recently, the rapid advancement of large language models has demonstrated a significant potential to transform OMC. However, most studies have primarily focused on improving diagnostic accuracy under conditions of relatively sufficient information, while paying limited attention to the "inquiry" phase of the consultation process. This lack of focus has left the relationship between "inquiry" and "diagnosis" insufficiently explored. In this paper, we first extract real patient interaction strategies from authentic doctor-patient conversations and use these strategies to guide the training of a patient simulator that closely mirrors real-world behavior. By inputting medical records into our patient simulator to simulate patient responses, we conduct extensive experiments to explore the relationship between "inquiry" and "diagnosis" in the consultation process. Experimental results demonstrate that inquiry and diagnosis adhere to the Liebig's law: poor inquiry quality limits the effectiveness of diagnosis, regardless of diagnostic capability, and vice versa. Furthermore, the experiments reveal significant differences in the inquiry performance of various models. To investigate this phenomenon, we categorize the inquiry process into four types: (1) chief complaint inquiry; (2) specification of known symptoms; (3) inquiry about accompanying symptoms; and (4) gathering family or medical history. We analyze the distribution of inquiries across the four types for different models to explore the reasons behind their significant performance differences. We plan to open-source the weights and related code of our patient simulator at https://github.com/LIO-H-ZEN/PatientSimulator.

Large Language Models with transformer architecture have revolutionized the domain of text generation, setting unprecedented benchmarks. Despite their impressive capabilities, LLMs have been criticized for generating outcomes that deviate from factual accuracy or display logical inconsistencies, phenomena commonly referred to as hallucinations. This term, however, has often been misapplied to any results deviating from the instructor's expectations, which this paper defines as attention misdirection rather than true hallucinations. Understanding the distinction between hallucinations and attention misdirection becomes increasingly relevant in business contexts, where the ramifications of such errors can significantly impact the value extraction from these inherently pre-trained models. This paper highlights the best practices of the PGI, Persona, Grouping, and Intelligence, method, a strategic framework that achieved a remarkable error rate of only 3,15 percent across 4,000 responses generated by GPT in response to a real business challenge. It emphasizes that by equipping experimentation with knowledge, businesses can unlock opportunities for innovation through the use of these natively pre-trained models. This reinforces the notion that strategic application grounded in a skilled team can maximize the benefits of emergent technologies such as the LLMs.

This study investigates the consistency of feedback ratings generated by OpenAI's GPT-4, a state-of-the-art artificial intelligence language model, across multiple iterations, time spans and stylistic variations. The model rated responses to tasks within the Higher Education (HE) subject domain of macroeconomics in terms of their content and style. Statistical analysis was conducted in order to learn more about the interrater reliability, consistency of the ratings across iterations and the correlation between ratings in terms of content and style. The results revealed a high interrater reliability with ICC scores ranging between 0.94 and 0.99 for different timespans, suggesting that GPT-4 is capable of generating consistent ratings across repetitions with a clear prompt. Style and content ratings show a high correlation of 0.87. When applying a non-adequate style the average content ratings remained constant, while style ratings decreased, which indicates that the large language model (LLM) effectively distinguishes between these two criteria during evaluation. The prompt used in this study is furthermore presented and explained. Further research is necessary to assess the robustness and reliability of AI models in various use cases.

Given the rapid ascent of large language models (LLMs), we study the question: (How) can large language models help in reviewing of scientific papers or proposals? We first conduct some pilot studies where we find that (i) GPT-4 outperforms other LLMs (Bard, Vicuna, Koala, Alpaca, LLaMa, Dolly, OpenAssistant, StableLM), and (ii) prompting with a specific question (e.g., to identify errors) outperforms prompting to simply write a review. With these insights, we study the use of LLMs (specifically, GPT-4) for three tasks: 1. Identifying errors: We construct 13 short computer science papers each with a deliberately inserted error, and ask the LLM to check for the correctness of these papers. We observe that the LLM finds errors in 7 of them, spanning both mathematical and conceptual errors. 2. Verifying checklists: We task the LLM to verify 16 closed-ended checklist questions in the respective sections of 15 NeurIPS 2022 papers. We find that across 119 {checklist question, paper} pairs, the LLM had an 86.6% accuracy. 3. Choosing the "better" paper: We generate 10 pairs of abstracts, deliberately designing each pair in such a way that one abstract was clearly superior than the other. The LLM, however, struggled to discern these relatively straightforward distinctions accurately, committing errors in its evaluations for 6 out of the 10 pairs. Based on these experiments, we think that LLMs have a promising use as reviewing assistants for specific reviewing tasks, but not (yet) for complete evaluations of papers or proposals.

With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has emerged as a promising approach for alignment, acting as an RL-free alternative to Reinforcement Learning from Human Feedback (RLHF). Despite DPO's various advancements and inherent limitations, an in-depth review of these aspects is currently lacking in the literature. In this work, we present a comprehensive review of the challenges and opportunities in DPO, covering theoretical analyses, variants, relevant preference datasets, and applications. Specifically, we categorize recent studies on DPO based on key research questions to provide a thorough understanding of DPO's current landscape. Additionally, we propose several future research directions to offer insights on model alignment for the research community.

With LLMs shifting their role from statistical modeling of language to serving as general-purpose AI agents, how should LLM evaluations change? Arguably, a key ability of an AI agent is to flexibly combine, as needed, the basic skills it has learned. The capability to combine skills plays an important role in (human) pedagogy and also in a paper on emergence phenomena (Arora & Goyal, 2023). This work introduces Skill-Mix, a new evaluation to measure ability to combine skills. Using a list of N skills the evaluator repeatedly picks random subsets of k skills and asks the LLM to produce text combining that subset of skills. Since the number of subsets grows like N^k, for even modest k this evaluation will, with high probability, require the LLM to produce text significantly different from any text in the training set. The paper develops a methodology for (a) designing and administering such an evaluation, and (b) automatic grading (plus spot-checking by humans) of the results using GPT-4 as well as the open LLaMA-2 70B model. Administering a version of to popular chatbots gave results that, while generally in line with prior expectations, contained surprises. Sizeable differences exist among model capabilities that are not captured by their ranking on popular LLM leaderboards ("cramming for the leaderboard"). Furthermore, simple probability calculations indicate that GPT-4's reasonable performance on k=5 is suggestive of going beyond "stochastic parrot" behavior (Bender et al., 2021), i.e., it combines skills in ways that it had not seen during training. We sketch how the methodology can lead to a Skill-Mix based eco-system of open evaluations for AI capabilities of future models.

Developing questions that are pedagogically sound, relevant, and promote learning is a challenging and time-consuming task for educators. Modern-day large language models (LLMs) generate high-quality content across multiple domains, potentially helping educators to develop high-quality questions. Automated educational question generation (AEQG) is important in scaling online education catering to a diverse student population. Past attempts at AEQG have shown limited abilities to generate questions at higher cognitive levels. In this study, we examine the ability of five state-of-the-art LLMs of different sizes to generate diverse and high-quality questions of different cognitive levels, as defined by Bloom's taxonomy. We use advanced prompting techniques with varying complexity for AEQG. We conducted expert and LLM-based evaluations to assess the linguistic and pedagogical relevance and quality of the questions. Our findings suggest that LLms can generate relevant and high-quality educational questions of different cognitive levels when prompted with adequate information, although there is a significant variance in the performance of the five LLms considered. We also show that automated evaluation is not on par with human evaluation.

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. However, current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. In this study, we introduce LOVA3, an innovative framework named ``Learning tO Visual Question Answering, Asking and Assessment,'' designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming at fostering the skills of asking and assessing questions in the context of images. To develop the questioning ability, we compile a comprehensive set of multimodal foundational tasks. For assessment, we introduce a new benchmark called EvalQABench, comprising 64,000 training samples (split evenly between positive and negative samples) and 5,000 testing samples. We posit that enhancing MLLMs with the capabilities to answer, ask, and assess questions will improve their multimodal comprehension and lead to better performance. We validate our hypothesis by training an MLLM using the LOVA3 framework and testing it on 10 multimodal benchmarks. The results demonstrate consistent performance improvements, thereby confirming the efficacy of our approach.

Assessment and evaluation have long been critical challenges in artificial intelligence (AI) and natural language processing (NLP). However, traditional methods, whether matching-based or embedding-based, often fall short of judging subtle attributes and delivering satisfactory results. Recent advancements in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm, where LLMs are leveraged to perform scoring, ranking, or selection across various tasks and applications. This paper provides a comprehensive survey of LLM-based judgment and assessment, offering an in-depth overview to advance this emerging field. We begin by giving detailed definitions from both input and output perspectives. Then we introduce a comprehensive taxonomy to explore LLM-as-a-judge from three dimensions: what to judge, how to judge and where to judge. Finally, we compile benchmarks for evaluating LLM-as-a-judge and highlight key challenges and promising directions, aiming to provide valuable insights and inspire future research in this promising research area. Paper list and more resources about LLM-as-a-judge can be found at https://github.com/llm-as-a-judge/Awesome-LLM-as-a-judge and https://llm-as-a-judge.github.io.

The emergence of ChatGPT has generated much speculation in the press about its potential to disrupt social and economic systems. Its astonishing language ability has aroused strong curiosity among scholars about its performance in different domains. There have been many studies evaluating the ability of ChatGPT and GPT-4 in different tasks and disciplines. However, a comprehensive review summarizing the collective assessment findings is lacking. The objective of this survey is to thoroughly analyze prior assessments of ChatGPT and GPT-4, focusing on its language and reasoning abilities, scientific knowledge, and ethical considerations. Furthermore, an examination of the existing evaluation methods is conducted, offering several recommendations for future research in evaluating large language models.

Language models (LMs) should provide reliable confidence estimates to help users detect mistakes in their outputs and defer to human experts when necessary. Asking a language model to assess its confidence ("Score your confidence from 0-1.") is a natural way of evaluating its uncertainty. However, models struggle to provide absolute assessments of confidence (i.e. judging confidence in answering a question independent of other questions) and the coarse-grained scores they produce are not useful for evaluating the correctness of their answers. We propose relative confidence estimation, where we match up questions against each other and ask the model to make relative judgments of confidence ("Which question are you more confident in answering correctly?"). Treating each question as a "player" in a series of matchups against other questions and the model's preferences as match outcomes, we can use rank aggregation methods like Elo rating and Bradley-Terry to translate the model's confidence preferences into confidence scores. We evaluate relative confidence estimation against absolute confidence estimation and self-consistency confidence methods on five state-of-the-art LMs -- GPT-4, GPT-4o, Gemini 1.5 Pro, Claude 3.5 Sonnet, and Llama 3.1 405B -- across 14 challenging STEM, social science, and commonsense reasoning question answering tasks. Our results demonstrate that relative confidence estimation consistently provides more reliable confidence scores than absolute confidence estimation, with average gains of 3.5% in selective classification AUC over direct absolute confidence estimation methods and 1.7% over self-consistency approaches across all models and datasets.

Peer assessment has been widely applied across diverse academic fields over the last few decades and has demonstrated its effectiveness. However, the advantages of peer assessment can only be achieved with high-quality peer reviews. Previous studies have found that high-quality review comments usually comprise several features (e.g., contain suggestions, mention problems, use a positive tone). Thus, researchers have attempted to evaluate peer-review comments by detecting different features using various machine learning and deep learning models. However, there is no single study that investigates using a multi-task learning (MTL) model to detect multiple features simultaneously. This paper presents two MTL models for evaluating peer-review comments by leveraging the state-of-the-art pre-trained language representation models BERT and DistilBERT. Our results demonstrate that BERT-based models significantly outperform previous GloVe-based methods by around 6% in F1-score on tasks of detecting a single feature, and MTL further improves performance while reducing model size.

Large language model (LLM)-based evaluation pipelines have demonstrated their capability to robustly evaluate machine-generated text. Extending this methodology to assess human-written text could significantly benefit educational settings by providing direct feedback to enhance writing skills, although this application is not straightforward. In this paper, we investigate whether LLMs can effectively assess human-written text for educational purposes. We collected 100 texts from 32 Korean students across 15 types of writing and employed GPT-4-Turbo to evaluate them using grammaticality, fluency, coherence, consistency, and relevance as criteria. Our analyses indicate that LLM evaluators can reliably assess grammaticality and fluency, as well as more objective types of writing, though they struggle with other criteria and types of writing. We publicly release our dataset and feedback.

Massive open online courses (MOOCs) unlock the doors to free education for anyone around the globe with access to a computer and the internet. Despite this democratization of learning, the massive enrollment in these courses means it is almost impossible for one instructor to assess every student's writing assignment. As a result, peer grading, often guided by a straightforward rubric, is the method of choice. While convenient, peer grading often falls short in terms of reliability and validity. In this study, using 18 distinct settings, we explore the feasibility of leveraging large language models (LLMs) to replace peer grading in MOOCs. Specifically, we focus on two state-of-the-art LLMs: GPT-4 and GPT-3.5, across three distinct courses: Introductory Astronomy, Astrobiology, and the History and Philosophy of Astronomy. To instruct LLMs, we use three different prompts based on a variant of the zero-shot chain-of-thought (Zero-shot-CoT) prompting technique: Zero-shot-CoT combined with instructor-provided correct answers; Zero-shot-CoT in conjunction with both instructor-formulated answers and rubrics; and Zero-shot-CoT with instructor-offered correct answers and LLM-generated rubrics. Our results show that Zero-shot-CoT, when integrated with instructor-provided answers and rubrics, produces grades that are more aligned with those assigned by instructors compared to peer grading. However, the History and Philosophy of Astronomy course proves to be more challenging in terms of grading as opposed to other courses. Finally, our study reveals a promising direction for automating grading systems for MOOCs, especially in subjects with well-defined rubrics.

LLMs are typically trained to answer user questions or follow instructions similarly to how human experts respond. However, in the standard alignment framework they lack the basic ability of explicit thinking before answering. Thinking is important for complex questions that require reasoning and planning -- but can be applied to any task. We propose a training method for equipping existing LLMs with such thinking abilities for general instruction following without use of additional human data. We achieve this by an iterative search and optimization procedure that explores the space of possible thought generations, allowing the model to learn how to think without direct supervision. For each instruction, the thought candidates are scored using a judge model to evaluate their responses only, and then optimized via preference optimization. We show that this procedure leads to superior performance on AlpacaEval and Arena-Hard, and shows gains from thinking on non-reasoning categories such as marketing, health and general knowledge, in addition to more traditional reasoning & problem-solving tasks.

Foundation models have rapidly permeated society, catalyzing a wave of generative AI applications spanning enterprise and consumer-facing contexts. While the societal impact of foundation models is growing, transparency is on the decline, mirroring the opacity that has plagued past digital technologies (e.g. social media). Reversing this trend is essential: transparency is a vital precondition for public accountability, scientific innovation, and effective governance. To assess the transparency of the foundation model ecosystem and help improve transparency over time, we introduce the Foundation Model Transparency Index. The Foundation Model Transparency Index specifies 100 fine-grained indicators that comprehensively codify transparency for foundation models, spanning the upstream resources used to build a foundation model (e.g data, labor, compute), details about the model itself (e.g. size, capabilities, risks), and the downstream use (e.g. distribution channels, usage policies, affected geographies). We score 10 major foundation model developers (e.g. OpenAI, Google, Meta) against the 100 indicators to assess their transparency. To facilitate and standardize assessment, we score developers in relation to their practices for their flagship foundation model (e.g. GPT-4 for OpenAI, PaLM 2 for Google, Llama 2 for Meta). We present 10 top-level findings about the foundation model ecosystem: for example, no developer currently discloses significant information about the downstream impact of its flagship model, such as the number of users, affected market sectors, or how users can seek redress for harm. Overall, the Foundation Model Transparency Index establishes the level of transparency today to drive progress on foundation model governance via industry standards and regulatory intervention.

Direct preference optimization (DPO) is a successful fine-tuning strategy for aligning large language models with human preferences without the need to train a reward model or employ reinforcement learning. DPO, as originally formulated, relies on binary preference data and fine-tunes a language model to increase the likelihood of a preferred response over a dispreferred response. However, not all preference pairs are equal: while in some cases the preferred response is only slightly better than the dispreferred response, there can be a stronger preference for one response when, for example, the other response includes harmful or toxic content. In this paper, we propose a generalization of DPO, termed DPO with an offset (ODPO), that does not treat every preference pair equally during fine-tuning. Intuitively, ODPO requires the difference between the likelihood of the preferred and dispreferred response to be greater than an offset value. The offset is determined based on the extent to which one response is preferred over another. Our experiments on various tasks suggest that ODPO significantly outperforms DPO in aligning language models, especially when the number of preference pairs is limited.

Recent work has highlighted the culturally-contingent nature of commonsense knowledge. We introduce AMAMMER{epsilon}, a test set of 525 multiple-choice questions designed to evaluate the commonsense knowledge of English LLMs, relative to the cultural contexts of Ghana and the United States. To create AMAMMER{epsilon}, we select a set of multiple-choice questions (MCQs) from existing commonsense datasets and rewrite them in a multi-stage process involving surveys of Ghanaian and U.S. participants. In three rounds of surveys, participants from both pools are solicited to (1) write correct and incorrect answer choices, (2) rate individual answer choices on a 5-point Likert scale, and (3) select the best answer choice from the newly-constructed MCQ items, in a final validation step. By engaging participants at multiple stages, our procedure ensures that participant perspectives are incorporated both in the creation and validation of test items, resulting in high levels of agreement within each pool. We evaluate several off-the-shelf English LLMs on AMAMMER{epsilon}. Uniformly, models prefer answers choices that align with the preferences of U.S. annotators over Ghanaian annotators. Additionally, when test items specify a cultural context (Ghana or the U.S.), models exhibit some ability to adapt, but performance is consistently better in U.S. contexts than Ghanaian. As large resources are devoted to the advancement of English LLMs, our findings underscore the need for culturally adaptable models and evaluations to meet the needs of diverse English-speaking populations around the world.

The zero-shot chain of thought (CoT) approach is often used in question answering (QA) by language models (LMs) for tasks that require multiple reasoning steps, typically enhanced by the prompt "Let's think step by step." However, some QA tasks hinge more on accessing relevant knowledge than on chaining reasoning steps. We introduce a simple general prompting technique, called PREP, that involves using two instances of LMs: the first (LM1) generates relevant information, and the second (LM2) answers the question based on this information. PREP is designed to be general and independent of the user's domain knowledge, making it applicable across various QA tasks without the need for specialized prompt engineering. To evaluate the effectiveness of our prompting method, we create a dataset of 100 binary-choice questions, derived from an extensive schematic dataset on artifact parts and material composition. These questions ask which of two artifacts is less likely to share materials with another artifact. Such questions probe the LM's knowledge of shared materials in the part structure of different artifacts. We test our method on our dataset and three published commonsense reasoning datasets. The average accuracy of our method is consistently higher than that of all the other tested methods across all the tested datasets.

Developing an educational test can be expensive and time-consuming, as each item must be written by experts and then evaluated by collecting hundreds of student responses. Moreover, many tests require multiple distinct sets of questions administered throughout the school year to closely monitor students' progress, known as parallel tests. In this study, we focus on tests of silent sentence reading efficiency, used to assess students' reading ability over time. To generate high-quality parallel tests, we propose to fine-tune large language models (LLMs) to simulate how previous students would have responded to unseen items. With these simulated responses, we can estimate each item's difficulty and ambiguity. We first use GPT-4 to generate new test items following a list of expert-developed rules and then apply a fine-tuned LLM to filter the items based on criteria from psychological measurements. We also propose an optimal-transport-inspired technique for generating parallel tests and show the generated tests closely correspond to the original test's difficulty and reliability based on crowdworker responses. Our evaluation of a generated test with 234 students from grades 2 to 8 produces test scores highly correlated (r=0.93) to those of a standard test form written by human experts and evaluated across thousands of K-12 students.

Recent advancements in natural language processing by large language models (LLMs), such as GPT-4, have been suggested to approach Artificial General Intelligence. And yet, it is still under dispute whether LLMs possess similar reasoning abilities to humans. This study evaluates GPT-4 and various other LLMs in judging the profoundness of mundane, motivational, and pseudo-profound statements. We found a significant statement-to-statement correlation between the LLMs and humans, irrespective of the type of statements and the prompting technique used. However, LLMs systematically overestimate the profoundness of nonsensical statements, with the exception of Tk-instruct, which uniquely underestimates the profoundness of statements. Only few-shot learning prompts, as opposed to chain-of-thought prompting, draw LLMs ratings closer to humans. Furthermore, this work provides insights into the potential biases induced by Reinforcement Learning from Human Feedback (RLHF), inducing an increase in the bias to overestimate the profoundness of statements.

Legal practice has witnessed a sharp rise in products incorporating artificial intelligence (AI). Such tools are designed to assist with a wide range of core legal tasks, from search and summarization of caselaw to document drafting. But the large language models used in these tools are prone to "hallucinate," or make up false information, making their use risky in high-stakes domains. Recently, certain legal research providers have touted methods such as retrieval-augmented generation (RAG) as "eliminating" (Casetext, 2023) or "avoid[ing]" hallucinations (Thomson Reuters, 2023), or guaranteeing "hallucination-free" legal citations (LexisNexis, 2023). Because of the closed nature of these systems, systematically assessing these claims is challenging. In this article, we design and report on the first preregistered empirical evaluation of AI-driven legal research tools. We demonstrate that the providers' claims are overstated. While hallucinations are reduced relative to general-purpose chatbots (GPT-4), we find that the AI research tools made by LexisNexis (Lexis+ AI) and Thomson Reuters (Westlaw AI-Assisted Research and Ask Practical Law AI) each hallucinate between 17% and 33% of the time. We also document substantial differences between systems in responsiveness and accuracy. Our article makes four key contributions. It is the first to assess and report the performance of RAG-based proprietary legal AI tools. Second, it introduces a comprehensive, preregistered dataset for identifying and understanding vulnerabilities in these systems. Third, it proposes a clear typology for differentiating between hallucinations and accurate legal responses. Last, it provides evidence to inform the responsibilities of legal professionals in supervising and verifying AI outputs, which remains a central open question for the responsible integration of AI into law.

Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability. To address this void, we introduce the first such dataset, named IfQA, where each question is based on a counterfactual presupposition via an "if" clause. For example, if Los Angeles was on the east coast of the U.S., what would be the time difference between Los Angeles and Paris? Such questions require models to go beyond retrieving direct factual knowledge from the Web: they must identify the right information to retrieve and reason about an imagined situation that may even go against the facts built into their parameters. The IfQA dataset contains over 3,800 questions that were annotated annotated by crowdworkers on relevant Wikipedia passages. Empirical analysis reveals that the IfQA dataset is highly challenging for existing open-domain QA methods, including supervised retrieve-then-read pipeline methods (EM score 36.2), as well as recent few-shot approaches such as chain-of-thought prompting with GPT-3 (EM score 27.4). The unique challenges posed by the IfQA benchmark will push open-domain QA research on both retrieval and counterfactual reasoning fronts.

The growing capabilities of large language models (LLMs) have led to their use as substitutes for human feedback for training and assessing other LLMs. These methods often rely on `constitutions', written guidelines which a critic model uses to provide feedback and improve generations. We investigate how the choice of constitution affects feedback quality by using four different constitutions to improve patient-centered communication in medical interviews. In pairwise comparisons conducted by 215 human raters, we found that detailed constitutions led to better results regarding emotive qualities. However, none of the constitutions outperformed the baseline in learning more practically-oriented skills related to information gathering and provision. Our findings indicate that while detailed constitutions should be prioritised, there are possible limitations to the effectiveness of AI feedback as a reward signal in certain areas.

As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often overly simplistic, allowing models to perform uniformly well, making it difficult to distinguish their capabilities. Additionally, benchmarks typically rely on static question-answer pairs, which models might memorize or guess. To address these limitations, we introduce the Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models using dynamic question templates and improved metrics across multiple disciplines such as mathematics, cryptography, cybersecurity, and computer science. The accompanying DIA-Bench dataset, which includes 150 diverse and challenging task templates with mutable parameters, is presented in various formats such as text, PDFs, compiled binaries, and visual puzzles. Our framework introduces four new metrics to assess a model's reliability and confidence across multiple attempts. These metrics revealed that even simple questions are frequently answered incorrectly when posed in varying forms, highlighting significant gaps in models' reliability. Notably, models like GPT-4o tended to overestimate their mathematical abilities, while ChatGPT-4o demonstrated better decision-making and performance through effective tool usage. We evaluated eight state-of-the-art large language models (LLMs) using DIA-Bench, showing that current models struggle with complex tasks and often display unexpectedly low confidence, even with simpler questions. The DIA framework sets a new standard for assessing not only problem-solving but also a model's adaptive intelligence and ability to assess its own limitations. The dataset is publicly available on our project's website.

To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to specifying complex goals asks humans to judge during training which agent behaviors are safe and useful, but this approach can fail if the task is too complicated for a human to directly judge. To help address this concern, we propose training agents via self play on a zero sum debate game. Given a question or proposed action, two agents take turns making short statements up to a limit, then a human judges which of the agents gave the most true, useful information. In an analogy to complexity theory, debate with optimal play can answer any question in PSPACE given polynomial time judges (direct judging answers only NP questions). In practice, whether debate works involves empirical questions about humans and the tasks we want AIs to perform, plus theoretical questions about the meaning of AI alignment. We report results on an initial MNIST experiment where agents compete to convince a sparse classifier, boosting the classifier's accuracy from 59.4% to 88.9% given 6 pixels and from 48.2% to 85.2% given 4 pixels. Finally, we discuss theoretical and practical aspects of the debate model, focusing on potential weaknesses as the model scales up, and we propose future human and computer experiments to test these properties.

Large Language Model (LLM) integrations into applications like Microsoft365 suite and Google Workspace for creating/processing documents, emails, presentations, etc. has led to considerable enhancements in productivity and time savings. But as these integrations become more more complex, it is paramount to ensure that the quality of output from the LLM-integrated applications are relevant and appropriate for use. Identifying the need to develop robust evaluation approaches for natural language generation, wherein references/ground labels doesn't exist or isn't amply available, this paper introduces a novel framework called "SAGEval" which utilizes a critiquing Agent to provide feedback on scores generated by LLM evaluators. We show that the critiquing Agent is able to rectify scores from LLM evaluators, in absence of references/ground-truth labels, thereby reducing the need for labeled data even for complex NLG evaluation scenarios, like the generation of JSON-structured forms/surveys with responses in different styles like multiple choice, likert ratings, single choice questions, etc.

Large Language Models (LLMs) are increasingly relied upon to evaluate text outputs of other LLMs, thereby influencing leaderboards and development decisions. However, concerns persist over the accuracy of these assessments and the potential for misleading conclusions. In this work, we investigate the effectiveness of LLMs as evaluators for text generation tasks. We propose FBI, a novel framework designed to examine the proficiency of Evaluator LLMs in assessing four critical abilities in other LLMs: factual accuracy, instruction following, coherence in long-form writing, and reasoning proficiency. By introducing targeted perturbations in answers generated by LLMs, that clearly impact one of these key capabilities, we test whether an Evaluator LLM can detect these quality drops. By creating a total of 2400 perturbed answers covering 22 perturbation categories, we conduct a comprehensive study using different evaluation strategies on five prominent LLMs commonly used as evaluators in the literature. Our findings reveal significant shortcomings in current Evaluator LLMs, which failed to identify quality drops in over 50\% of cases on average. Single-answer and pairwise evaluations demonstrated notable limitations, whereas reference-based evaluations showed comparatively better performance. These results underscore the unreliable nature of current Evaluator LLMs and advocate for cautious implementation in practical applications. Code and data are available at https://github.com/AI4Bharat/FBI.

To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans. Over the past hundred years, there has been an abundance of attempts to define and measure intelligence, across both the fields of psychology and AI. We summarize and critically assess these definitions and evaluation approaches, while making apparent the two historical conceptions of intelligence that have implicitly guided them. We note that in practice, the contemporary AI community still gravitates towards benchmarking intelligence by comparing the skill exhibited by AIs and humans at specific tasks such as board games and video games. We argue that solely measuring skill at any given task falls short of measuring intelligence, because skill is heavily modulated by prior knowledge and experience: unlimited priors or unlimited training data allow experimenters to "buy" arbitrary levels of skills for a system, in a way that masks the system's own generalization power. We then articulate a new formal definition of intelligence based on Algorithmic Information Theory, describing intelligence as skill-acquisition efficiency and highlighting the concepts of scope, generalization difficulty, priors, and experience. Using this definition, we propose a set of guidelines for what a general AI benchmark should look like. Finally, we present a benchmark closely following these guidelines, the Abstraction and Reasoning Corpus (ARC), built upon an explicit set of priors designed to be as close as possible to innate human priors. We argue that ARC can be used to measure a human-like form of general fluid intelligence and that it enables fair general intelligence comparisons between AI systems and humans.

In today's fast-paced world, effective presentations have become an essential tool for communication in both online and offline meetings. The crafting of a compelling presentation requires significant time and effort, from gathering key insights to designing slides that convey information clearly and concisely. However, despite the wealth of resources available, people often find themselves manually extracting crucial points, analyzing data, and organizing content in a way that ensures clarity and impact. Furthermore, a successful presentation goes beyond just the slides; it demands rehearsal and the ability to weave a captivating narrative to fully engage the audience. Although there has been some exploration of automating document-to-slide generation, existing research is largely centered on converting research papers. In addition, automation of the delivery of these presentations has yet to be addressed. We introduce PASS, a pipeline used to generate slides from general Word documents, going beyond just research papers, which also automates the oral delivery of the generated slides. PASS analyzes user documents to create a dynamic, engaging presentation with an AI-generated voice. Additionally, we developed an LLM-based evaluation metric to assess our pipeline across three critical dimensions of presentations: relevance, coherence, and redundancy. The data and codes are available at https://github.com/AggarwalTushar/PASS.

We propose a new test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attain high accuracy on this test, models must possess extensive world knowledge and problem solving ability. We find that while most recent models have near random-chance accuracy, the very largest GPT-3 model improves over random chance by almost 20 percentage points on average. However, on every one of the 57 tasks, the best models still need substantial improvements before they can reach expert-level accuracy. Models also have lopsided performance and frequently do not know when they are wrong. Worse, they still have near-random accuracy on some socially important subjects such as morality and law. By comprehensively evaluating the breadth and depth of a model's academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.

Open-ended questions test a more thorough understanding than closed-ended questions and are often a preferred assessment method. However, open-ended questions are tedious to grade and subject to personal bias. Therefore, there have been efforts to speed up the grading process through automation. Short Answer Grading (SAG) systems aim to automatically score students' answers. Despite growth in SAG methods and capabilities, there exists no comprehensive short-answer grading benchmark across different subjects, grading scales, and distributions. Thus, it is hard to assess the capabilities of current automated grading methods in terms of their generalizability. In this preliminary work, we introduce the combined ASAG2024 benchmark to facilitate the comparison of automated grading systems. Combining seven commonly used short-answer grading datasets in a common structure and grading scale. For our benchmark, we evaluate a set of recent SAG methods, revealing that while LLM-based approaches reach new high scores, they still are far from reaching human performance. This opens up avenues for future research on human-machine SAG systems.