Musical Ethnocentrism in Large Language Models

2025-01-23

NLP4MUSA

AI Summary

This study identifies, for the first time, a pronounced Western-centric bias in large language models (LLMs) regarding music evaluation. Method: Two empirical experiments were conducted: (1) analyzing the nationality distribution of LLM-generated “Top 100 Music Contributors,” and (2) cross-cultural quantitative scoring of musical excerpts along culturally grounded dimensions—melody, harmony, rhythm, and timbre—using expert-validated frameworks. Models including ChatGPT and Mixtral consistently overrepresented Western contributors and systematically undervalued non-Western musical traditions. Contribution/Results: The study introduces the novel construct of *musico-ethnocentrism* and establishes the first LLM bias measurement paradigm tailored to music-specific cultural dimensions. It integrates prompt engineering, cross-cultural statistical analysis, and a mixed qualitative–quantitative evaluation framework. Findings confirm that LLMs encode structural cultural biases, providing both theoretical grounding and empirical evidence for advancing AI ethics and cultural equity in music AI research.

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Natural Language Processing: Ethics — Bias, Fairness, Transparency & PrivacyPhilosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationSearch and Retrieval-Augmented AI: Web evaluation methodologies and metricsWeb Mining and Content Analysis: Large pretrained models with web data

Abstract

Large Language Models (LLMs) reflect the biases in their training data and, by extension, those of the people who created this training data. Detecting, analyzing, and mitigating such biases is becoming a focus of research. One type of bias that has been understudied so far are geocultural biases. Those can be caused by an imbalance in the representation of different geographic regions and cultures in the training data, but also by value judgments contained therein. In this paper, we make a first step towards analyzing musical biases in LLMs, particularly ChatGPT and Mixtral. We conduct two experiments. In the first, we prompt LLMs to provide lists of the “Top 100” musical contributors of various categories and analyze their countries of origin. In the second experiment, we ask the LLMs to numerically rate various aspects of the musical cultures of different countries. Our results indicate a strong preference of the LLMs for Western music cultures in both experiments.

Problem

• Cultural Bias
• Large Language Models
• Music Evaluation

Innovation

• Cultural Bias
• Music Preferences
• AI Models