Year: 2026
Type: conference-paper
Abstract: The evaluation of music understanding in Large Audio-Language Models (LALMs) requires a rigorously defined benchmark that truly tests whether models can perceive and interpret music, a standard that current data methodologies frequently fail to meet.This paper introduces a meticulously structured approach to music evaluation, proposing a new dataset of 320 handwritten questions curated and validated by experts with musical training, arguing that such focused, manual curation is superior for probing complex audio comprehension.To demonstrate the use of the dataset, we benchmark six state-of-the-art LALMs and additionally test their robustness to uni-modal shortcuts.
Institutions: Universitat Pompeu Fabra, Universitat Autònoma de Barcelona
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: European Commission
OpenAlex ID: W7140082374