作者位次 #3/6ACL 2026Poster· Natural Language Processing
Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts
Xiaowei Yuan · Ziyang Huang · Zhao Yang · Yequan Wang · Jun Zhao · Kang Liu
摘要
Retrieval-Augmented Generation (RAG) has become a standard paradigm for grounding Large Language Models (LLMs) with external knowledge. However, RAG performance often degrades substantially when faced with noisy, outdated, or conflicting retrieved information. In this work, we empirically demonst...