Understanding Human Perception of Music Plagiarism Through a Computational Approach

2026-01-05

arXiv.org

AI Summary

This study addresses the disconnect between existing music plagiarism detection algorithms and human perceptual standards. To bridge this gap, the authors propose an interpretable evaluation framework that integrates three high-level musical features—melody, rhythm, and chord progression—and, for the first time, combines human perceptual mechanisms of musical plagiarism with large language models (LLMs). They introduce a stepwise LLM-as-a-Judge paradigm that systematically coordinates feature extraction with LLM-based reasoning. This approach not only uncovers the key criteria humans use to assess musical similarity and their tolerance for variation but also demonstrates significant effectiveness in emulating human subjective judgment in plagiarism assessment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

There is a wide variety of music similarity detection algorithms, while discussions about music plagiarism in the real world are often based on audience perceptions. Therefore, we aim to conduct a study to examine the key criteria of human perception of music plagiarism, focusing on the three commonly used musical features in similarity analysis: melody, rhythm, and chord progression. After identifying the key features and levels of variation humans use in perceiving musical similarity, we propose a LLM-as-a-judge framework that applies a systematic, step-by-step approach, drawing on modules that extract such high-level attributes.

Problem

• music plagiarism
• human perception
• music similarity
• melody
• rhythm

Innovation

• LLM-as-a-judge
• music plagiarism perception
• melody-rhythm-chord analysis
• computational music similarity
• human-centered evaluation