Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence
Paper
•
2503.05037
•
Published
•
4
UCLA NLP
university
AI & ML interests
Natural Language Processing, Bias and Fairness in NLP
Recent Activity
View all activity
uclanlp's activity
mohsenfayyaz
authored
a
paper
7 days ago
xiaowu0162
updated
a
model
14 days ago
kaiweichang
authored
a
paper
3 months ago
xqwu
updated
a
dataset
4 months ago
gordonhu
updated
a
dataset
4 months ago
kaiweichang
authored
a
paper
5 months ago
xiaowu0162
authored
a
paper
5 months ago
kaiweichang
authored
a
paper
5 months ago
violetpeng
authored
12
papers
5 months ago
Tractable Control for Autoregressive Language Generation
Paper
•
2304.07438
•
Published
Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
Paper
•
1904.10635
•
Published
The Woman Worked as a Babysitter: On Biases in Language Generation
Paper
•
1909.01326
•
Published
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems
Paper
•
2310.05280
•
Published
•
1
ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
Paper
•
2305.07797
•
Published
Mitigating Bias for Question Answering Models by Tracking Bias Influence
Paper
•
2310.08795
•
Published
"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters
Paper
•
2310.09219
•
Published
Evaluating Large Language Models on Controlled Generation Tasks
Paper
•
2310.14542
•
Published
Identifying Informational Sources in News Articles
Paper
•
2305.14904
•
Published
Code-Switched Text Synthesis in Unseen Language Pairs
Paper
•
2305.16724
•
Published
ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos
Paper
•
2311.01620
•
Published
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model
Paper
•
2305.16734
•
Published