Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts
Tri-PvP, an 8,000-sample tri-modal conflict benchmark crossing vision, audio, and text, is introduced, revealing a systematic asymmetry in evidence-form bias: models exhibit a stronger bias toward perceptual signal in vision but propositional in audio.
Yen-Ting Piao, Shu-Yun Chen, Chin-Hui Chu et al.
· 0 citations