cs.AI, cs.CL, cs.SD, eess.AS

All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation

arXiv:2604.24401v1 Announce Type: cross
Abstract: Large Audio-Language Models show consistent performance gains across speech and audio benchmarks, yet high scores may not reflect true auditory perception. If a model can answer questions without proce…