Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study
This work presents the first music-specific, layer-wise, multi-paradigm empirical study of hallucination in audio-language models and forms it as a hierarchical perceptual grounding failure across five layers: sound events, temporal properties, tonal attributes, style, and emotion.
Yu Liu, Jia-Hui Liu, Zhi-Lin Liu et al.
· 0 citations