作者位次 #4/9ACL 2026Poster· Natural Language Processing
Disco- RAG : Discourse-Aware Retrieval-Augmented Generation
Dongqi Liu · Hang Ding · Qiming Feng · Xurong Xie · Zhucun Xue · Chengjie Wang · Jian Li · Jiangning Zhang · Yabiao Wang
摘要
Retrieval-Augmented Generation (RAG) has emerged as an important means of enhancing the performance of large language models (LLMs) in knowledge-intensive tasks. However, most existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing...