作者位次 #3/8ACL 2026Poster· Natural Language Processing
S cene A lign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes
Chuhan Wang · Xintong Li · Jennifer Yuntong Zhang · Junda Wu · Chengkai Huang · Lina Yao · Julian J. McAuley · Jingbo Shang
摘要
Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as hallucinated entities, mis-grounded relations, skipped step...