作者位次 #7/11ACL 2026Poster· Natural Language Processing
LAD - RAG : Layout-aware Dynamic RAG for Visually-Rich Document Understanding
Zhivar Sourati · Zheng Wang · Marianne Menglin Liu · Yazhe Hu · Mengqing Guo · Sujeeth Bharadwaj · Kyu J. Han · Tao Sheng · Sujith Ravi · Morteza Dehghani · Dan Roth
摘要
Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents’ structural organization and cross-page dependencies. However, conventional retrieval-augmented generation (RAG) methods encode content in isolated chunks during ingest...