作者位次 #2/10SIGIR 2026Poster· Information Retrieval (Short)
EviRAG: Evidence-Guided Retrieval-Augmented Generation for Medical Vision-Language Models
Yiyang Gu · Jiayue Fan · Kaili Liu · Bohan Wu · Binqi Chen · Zequn Liu · Zhiping Xiao · Rong-Cheng Tu · Xiao Luo · Ming Zhang
摘要
Retrieval-augmented generation (RAG) is widely adopted for radiology report generation with medical vision-language models, leveraging external reports as linguistic references. However, existing RAG methods rely primarily on dense embedding similarity, which may retrieve reports that are semanti...