作者位次 #3/7ACL 2026Findings· Findings of ACL
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
Xinping Zhao · Shouzheng Huang · Yan Zhong · Xinshuo Hu · Meishan Zhang · Baotian Hu · Min Zhang
摘要
Retrieval-Augmented Generation (RAG) effectively improves the accuracy of Large Language Models (LLMs). However, retrieval noises significantly undermine the quality of LLMs’ generation, necessitating the development of denoising mechanisms. Previous works extract evidence straightforwardly witho...