作者位次 #9/10ACL 2026Poster· ACL Industry Track
MM - B iz RAG : Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q & A
Hanoz Bhathena · Parin Rajesh Jhaveri · Rohan Mittal · Prateek Singh · Aymen Kallala · Rachneet Kaur · Yiqiao Jin · Zhen Zeng · Adwait Ratnaparkhi · Denis Kochedykov
摘要
Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and for answer generation. While efficient, this trend often neglects explicit handling of the rich, structured information in...