作者位次 #4/7ACL 2026Findings· Findings of ACL
From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG
Guanhua CHEN · Chuyue Huang · Yutong Yao · Shudong Liu · Xueqing Song · Lidia S. Chao · Derek F. Wong
摘要
Multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities (entire images or scenes), creating a mismatch with fine-grained user queries and making failures unverifiable. We introduce GranuVistaVQA, a multimodal benchmark featuring real-world landmarks with...