作者位次 #4/8ACL 2026Poster· Natural Language Processing
Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding
Wenqing Hou · Hongkui Tu · Ye Wang · Yue Zhang · Yuying Liu · Dong Zhu · Liqun Gao · Bin Zhou
摘要
The identification of harmful memes extends beyond a mere classification task, encompassing challenges related to multi-perspective semantic comprehension and hierarchical reasoning. Prevailing approaches predominantly depend on modal alignment or black-box classifiers, which fail to capture impl...