作者位次 #5/8ACL 2026Poster· Natural Language Processing
CIRAG : Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
Zili Wei · Yilin Wang · Xiaocui Yang · Shi Feng · Weidong Bao · Daling Wang · Zihan Wang · Yifei Zhang
摘要
Triple-based Iterative Retrieval-Augmented Generation (iRAG) mitigates document-level noise for multi-hop question answering. However, existing methods still face limitations: (i) greedy single-path expansion, which propagates early errors and fails to capture parallel evidence from different rea...