Resources for EMNLP 2024 Paper: Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring
J Li
jiazhengli
AI & ML interests
None yet
Recent Activity
liked
a dataset
about 6 hours ago
EleutherAI/SmolLM-135M-100b
liked
a dataset
about 6 hours ago
PleIAs/common_corpus
liked
a dataset
about 6 hours ago
Locutusque/UltraTextbooks
Organizations
None yet
Collections
3
Resources for EMNLP 2024 Paper: Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
-
jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO
Text Generation • Updated -
jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO
Text Generation • Updated • 1 -
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation • Updated • 3 • 1 -
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Paper • 2406.10957 • Published • 1
models
12
jiazhengli/Qwen2.5-7B-RoleMRC-sft
Updated
•
4
jiazhengli/Qwen2.5-7B-RoleMRC-dpo
Updated
jiazhengli/Llama-3.1-8B-RoleMRC-sft
Updated
•
4
jiazhengli/Llama-3.1-8B-RoleMRC-dpo
Updated
•
2
jiazhengli/long-t5-tglobal-large-AERA
Text2Text Generation
•
Updated
jiazhengli/Mixtral-8x7B-Instruct-v0.1-QLoRA-Assessment-Rationale-dpo
Updated
jiazhengli/Mixtral-8x7B-Instruct-v0.1-QLoRA-Assessment-Rationale-sft
Updated
•
1
jiazhengli/Meta-Llama-3-8B-QLoRA-Assessment-Rationale-sft
Updated
•
1
jiazhengli/Meta-Llama-3-8B-QLoRA-Assessment-Rationale-dpo
Updated
•
1
jiazhengli/deberta-v3-large-Rationale-to-Score
Text Classification
•
Updated
•
4
•
1