作者位次 #3/6SIGIR 2026Oral· Information Retrieval (Full)
Incentivizing Retrieval-Augmented Generation via Inner Adaptive Context Selection
Chenxu Cui · Lin Shen · Haihui Fan · Sa Zhu · Feifei Dai · Bo Li
摘要
Retrieval-Augmented Generation (RAG) techniques have emerged as a promising direction to merge the non-parametric knowledge into Large Language Models (LLMs), thereby alleviating factual errors, hallucinations and outdated knowledge. Existing RAG methods, which append multiple retrieved documents...