4 papers · 1 filter
Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
Ruizhe Li, Chen Chen, Yuchen Hu +3
Retrieval-Augmented Generation (RAG) leverages large language models (LLMs) combined with external contexts to enhance the accuracy and reliability of generated responses. However,…
Race, Ethnicity and Their Implication on Bias in Large Language Models
Shiyue Hu, Ruizhe Li, Yanjun Gao
Large language models (LLMs) increasingly operate in high-stakes settings including healthcare and medicine, where demographic attributes such as race and ethnicity may be explicit…
Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes
Quintin Myers, Yanjun Gao
Large language models (LLMs) are increasingly proposed for detecting and responding to violent content online, yet their ability to reason about morally ambiguous, real-world scena…
Learning to Maximize Mutual Information for Chain-of-Thought Distillation
Xin Chen, Hanxian Huang, Yanjun Gao +3
Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by…