Don't CLAP: Are Music-Text Models Bag-of-Words?

Excerpt

arXiv:2609.30540v1 Announce Type: cross Abstract: Text-to-music systems are assessed on audio quality and on how faithfully the music follows its prompt, and the CLAP score, the cosine similarity between a music-text model's audio and text embeddings, is the standard objective metric of faithfulness. We ask how accurately that score reflects the text: when an attribute is linked to an instrument (e.g., distorted guitar), does the text embedding capture that binding? To find out, we introduce an