Okinawa Institute of Science and Technology Graduate University

Deleting the waveform region an audio-language model's claim points to overturns its "sound present" answer more often than deleting an equally sized random window, indicating that these hallucinations are at least partly grounded in locatable audio evidence, and the same contrast lifts Qwen2-Audio accuracy from 57.1% to 71.9%.

Deleting the waveform region an audio-language model's claim points to overturns its "sound present" answer more often than deleting an equally sized random window, indicating that these hallucinations are at least partly grounded in locatable audio evidence, and the same contrast lifts Qwen2-Audio accuracy from 57.1% to 71.9%.