Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Token-weighted Direct Preference Optimization with Attention
Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1
Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses e…
cs.CL2025
Judging with Confidence: Calibrating Autoraters to Preference Distributions
Zhuohang Li, Xiaowei Li, Chengyu Huang +11
The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limite…
cs.CL2024
Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation
Zhuohang Li, Jiaxin Zhang, Chao Yan +4
Language models (LMs) are known to suffer from hallucinations and misinformation. Retrieval augmented generation (RAG) that retrieves verifiable information from an external knowle…