Evaluates eight frontier MLLMs on a new dataset of 200 annotated Chinese short videos for detecting deceptive patterns and cognitive biases, with Gemini-2.5-Pro scoring highest at 71.5/100 belief in multimodal setting.
Jinpeng You, Yanghao Lin, Dazhen Lin, and Donglin Cao
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation
Evaluates eight frontier MLLMs on a new dataset of 200 annotated Chinese short videos for detecting deceptive patterns and cognitive biases, with Gemini-2.5-Pro scoring highest at 71.5/100 belief in multimodal setting.