Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
Jiaying Wu · Fanxiao Li · Zihang Fu · Min-Yen Kan · Bryan Hooi
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Jiaying Wu · Fanxiao Li · Zihang Fu · Min-Yen Kan · Bryan Hooi
Jiaying Wu · Zihang Fu · Haonan Wang · Fanxiao Li · Jiafeng Guo · Preslav Nakov · Min-Yen Kan
Community Notes, the crowd-sourced misinformation governance system on X (formerly Twitter), allows users to flag misleading posts, attach contextual notes, and rate the notes’ helpfulness. However, our empirical analysis of 30.8K health-related notes reveals substantial latency, with a median de...
Fanxiao Li · Jiaying Wu · Tingchao Fu · Dayang Li · Herun Wan · Wei Zhou · Min-Yen Kan
Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports. This covert harm is subtler than explicit misinformation,...
Tingchao Fu · Wenkai Wang · Fanxiao Li · Huadong Zhang · Jinhong Zhang · Dayang Li · Yunyun Dong · Renyang Liu · Wei Zhou
Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updat...
Fanxiao Li · Jiaying Wu · Tingchao Fu · Yunyun Dong · Bingbing Song · Wei Zhou