作者位次 #3/6ACL 2026Poster· Natural Language Processing
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
Weiqing Luo · Zongye Hu · Xiao Wang · Zhiyuan Yu · Haofeng Zhang · Ziyi Huang
摘要
Visual evidence selection is a critical component of multimodal retrieval-augmented generation (RAG), yet existing methods typically rely on semantic relevance or surface-level similarity, which are often misaligned with the actual utility of visual evidence for downstream reasoning. We reformula...