Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models 事件

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models arXiv:2606.05161v1 Announce Type: cross Abstract: Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We examine this question using a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text,