5 papers
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
Jiaang Li, Zhendong Mao, Quan Wang +2
Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhi…
In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback
Mingye Zhu, Yi Liu, Zheren Fu +2
Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as…
Leveraging Robust Optimization for LLM Alignment under Distribution Shifts
Mingye Zhu, Yi Liu, Zheren Fu +2
Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rel…
Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability
Chiwei Zhu, Benfeng Xu, An Yang +4
Training language models with rationales augmentation has been shown to be beneficial in many existing works. In this paper, we identify that such a prevailing view does not hold c…
ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
Jiaang Li, Quan Wang, Zhongnan Wang +2
Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for…