MusGO: A Community-Driven Framework For Assessing Openness in Music-Generative AI

2025-07-04

AI Summary

The music generation AI community has long lacked a clear, operational definition and evaluation framework for “openness,” impeding transparency, accountability, and copyright compliance. Method: We introduce MusGO—the first community-driven, evidence-based openness assessment framework for music AI—adapting large language model openness evaluation paradigms to the Music Information Retrieval (MIR) domain. Grounded in feedback from 110 MIR researchers, MusGO defines a 13-dimensional openness taxonomy and implements a multi-criteria, evidence-anchored scoring methodology. Its publicly accessible, verifiable, and continuously updatable leaderboard ensures reproducibility and extensibility. Contribution/Results: We systematically evaluate 16 state-of-the-art music generation models, releasing the first reproducible, scalable openness benchmark. MusGO establishes both theoretical foundations and practical tools for responsible governance of music AI systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Algorithmic accountability and transparency on the web
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

Since 2023, generative AI has rapidly advanced in the music domain. Despite significant technological advancements, music-generative models raise critical ethical challenges, including a lack of transparency and accountability, along with risks such as the replication of artists' works, which highlights the importance of fostering openness. With upcoming regulations such as the EU AI Act encouraging open models, many generative models are being released labelled as 'open'. However, the definition of an open model remains widely debated. In this article, we adapt a recently proposed evidence-based framework for assessing openness in LLMs to the music domain. Using feedback from a survey of 110 participants from the Music Information Retrieval (MIR) community, we refine the framework into MusGO (Music-Generative Open AI), which comprises 13 openness categories: 8 essential and 5 desirable. We evaluate 16 state-of-the-art generative models and provide an openness leaderboard that is fully open to public scrutiny and community contributions. Through this work, we aim to clarify the concept of openness in music-generative AI and promote its transparent and responsible development.

Problem

• Assessing openness in music-generative AI models
• Addressing lack of transparency and accountability in AI music generation
• Clarifying and promoting responsible development of open music-generative AI

Innovation

• Adapts LLM openness framework to music AI
• Refines framework via MIR community feedback
• Creates openness leaderboard for public scrutiny