作者位次 #3/7ACL 2026Findings· Findings of ACL
M ed KI nstruct: A Multimodal Knowledge Graph Based Framework for Multi-Hop and Hard-Negative Instruction Data Synthesis in M ed VQA
Yinan Wu · Jihang Jin · Xuhao Bao · Weiyan Zhang · Hanjing Yan · Tong Ruan · ChunMing Wang
摘要
Medical visual question answering (MedVQA) requires models to provide accurate answers given a medical image and a corresponding question. Recently, instruction tuning of general large vision–language models (LVLMs) has become a dominant paradigm for this task, enabling open-ended predictions and...