Genre Bias or Aesthetic Perception? Identifying and Mitigating Shortcut Learning in Music Evaluation

2026-07-15

AI Summary

This study addresses the tendency of existing music aesthetic scoring models to rely on genre-related features as shortcuts due to training data bias, resulting in overestimation of popular music and underestimation of other high-quality genres—diverging from human aesthetic preferences. For the first time, this work systematically identifies and quantifies the problem of genre-induced shortcut learning in music evaluation. To mitigate this issue, the authors propose a novel training paradigm that integrates hard example reweighting with group performance regularization, aiming to learn genre-invariant representations of musicality. The proposed approach significantly reduces model dependence on genre cues and improves alignment with human preferences across both cross-genre and within-genre settings, effectively balancing sample difficulty and group fairness.

Abstract

Music aesthetics scoring plays a critical role in applications such as dataset curation, generative model evaluation, and reward modeling for music generation. Recent approaches rely on deep neural networks trained on human-annotated ratings, but these models may exploit spurious correlations rather than capturing perceptually meaningful aesthetics. In this work, we identify a previously underexplored failure mode in music evaluation models: genre-induced shortcut learning. Through a systematic analysis of SongEval, we show that biases in training data lead to strong correlations between genre-related features and predicted scores, causing the model to use them as a proxy for aesthetics. This results in systematic overestimation of pop music and undervaluation of high-quality samples from other genres, leading to predictions that are inconsistent with human preferences. To address this issue, we propose a training objective that jointly reweights hard samples and regularizes group-level performance, encouraging the model to learn genre-invariant representations of musicality. Experimental results demonstrate that our method reduces genre-dependent bias and improves alignment with human preferences, as reflected by gains in both cross-genre and within-genre preference alignment.

Problem

• shortcut learning
• genre bias
• music aesthetics
• evaluation bias
• spurious correlation

Innovation

• shortcut learning
• genre bias
• music aesthetics
• invariant representation
• preference alignment