Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
Reward Difference Optimization For Sample Reweighting In Offline RLHF
Shiqi Wang, Zhengze Zhang, Rui Zhao +2
With the rapid advances in Large Language Models (LLMs), aligning LLMs with human preferences become increasingly important. Although Reinforcement Learning with Human Feedback (RL…
cs.CL2024
Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization
Shiqi Wang, Yeqin Zhang, Cam-Tu Nguyen
In open-domain Question Answering (QA), dense retrieval is crucial for finding relevant passages for answer generation. Typically, contrastive learning is used to train a retrieval…