SOURCE-LINKED INTELLIGENCE

Knowing When Not to Answer: Pseudo-Ensembles for Abstention in Music Audio-Language Models

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Music audio-language models are evaluated almost entirely by accuracy on multiple-choice questions. This protocol forces the model to commit to an option, so a lucky guess looks the same as real musical understanding. What is missing is a way to tell when the model does not know the answer, so that it can abstain instead of guessing. The usual solution, an ensemble of independently trained models, is far too expensive here, which leaves the entropy of a single predictive distribution as the only available confidence signal. We instead build pseudo-ensembles from one pretrained model by perturb

Read original source ↗ Open in workspace

recordType

paper

region

Global