Exploring LLMs for South Asian Music Understanding and Generation

• URL: http://arxiv.org/abs/2606.05522v1
• Date: Wed, 03 Jun 2026 23:53:27 GMT
• Title: Exploring LLMs for South Asian Music Understanding and Generation
• Abstract summary: We present the first systematic evaluation of Large Language Models (LLMs) competence in South Asian classical music.<n>For music understanding evaluation, we introduce a 504-question-answer benchmark spanning raga grammar, cultural knowledge, and symbolic notation reasoning.<n>For music generation, we design a five-level controlled prompting framework and find that even the strongest model produces stylistically faithful outputs only 40% of the time.
• Score: 1.615773498306309
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in Large Language Models (LLMs) have shown promising results in music understanding and generation tasks. However, existing works remain confined to Western tonal traditions, offering little insight into whether current LLMs can handle structurally distinct low-resource musical traditions. We present the first systematic evaluation of LLM competence in South Asian classical music, a tradition governed by raga, tala-based melodic constraints that impose fundamentally different structural principles from Western harmony-driven music. We ground our evaluation in Hindustani classical theory and Bengali classical forms, including Rabindra and Nazrul Sangeet -- representative low-resource traditions within South Asian classical music. For music understanding evaluation, we introduce a 504-question-answer benchmark spanning raga grammar, cultural knowledge, and symbolic notation reasoning, evaluating 33 LLMs where frontier models such as Gemini 2.5 Pro achieve 85-90% accuracy, while most open-source models remain in the 23-40% range. For music generation, we design a five-level controlled prompting framework and find that even the strongest model produces stylistically faithful outputs only 40% of the time. These results reveal that structural validity and stylistic faithfulness in music generation are distinct objectives and highlight an open challenge for culturally grounded music modeling.

Related papers

• Music Genre Classification: A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches [0.0]
  We construct a novel dataset of approximately 8,000 labeled 30-second audio clips spanning eight Nepali music genres.<n>We offer a culturally grounded interpretation of misclassification patterns that reflects genuine overlaps in Nepal's musical traditions.
  arXiv  Detail & Related papers  (2026-03-16T15:43:48Z)
• Do Large Language Models Truly Understand Cross-cultural Differences? [53.481048019144644]
  We develop a scenario-based benchmark to evaluate large language models' cross-cultural understanding and reasoning.<n>Grounded in cultural theory, we categorize cross-cultural capabilities into nine dimensions.<n>The dataset supports continuous expansion, and experiments confirm its transferability to other languages.
  arXiv  Detail & Related papers  (2025-12-08T01:21:58Z)
• Music Flamingo: Scaling Music Understanding in Audio Language Models [98.94537017112704]
  Music Flamingo is a novel large audio-language model designed to advance music understanding in foundational audio models.<n> MF-Skills is a dataset labeled through a multi-stage pipeline that yields rich captions and question-answer pairs covering harmony, structure, timbre, lyrics, and cultural context.<n>We introduce a post-training recipe: we first cold-start with MF-Think, a novel chain-of-thought dataset grounded in music theory, followed by GRPO-based reinforcement learning with custom rewards.
  arXiv  Detail & Related papers  (2025-11-13T13:21:09Z)
• CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning [55.80320947983555]
  CultureMERT-95M is a multi-culturally adapted foundation model developed to enhance cross-cultural music representation learning.<n>Training on a 650-hour multi-cultural data mix results in an average improvement of 4.9% in ROC-AUC and AP across diverse non-Western music auto-tagging tasks.<n>Task arithmetic performs on par with our multi-culturally trained model on non-Western auto-tagging tasks and shows no regression on Western datasets.
  arXiv  Detail & Related papers  (2025-06-21T21:16:39Z)
• Universal Music Representations? Evaluating Foundation Models on World Music Corpora [65.72891334156706]
  Foundation models have revolutionized music information retrieval, but questions remain about their ability to generalize.<n>This paper presents a comprehensive evaluation of five state-of-the-art audio foundation models across six musical corpora.
  arXiv  Detail & Related papers  (2025-06-20T15:06:44Z)
• YuE: Scaling Open Foundation Models for Long-Form Music Generation [172.52183330644303]
  YuE is a family of open foundation models based on the LLaMA2 architecture.<n>It generates up to five minutes of music while maintaining lyrical alignment, coherent musical structure, and engaging vocal melodies with appropriate accompaniment.
  arXiv  Detail & Related papers  (2025-03-11T17:26:50Z)
• Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models [13.568559786822457]
  We present a study of the datasets and research papers for music generation.<n>We find that only 5.7% of the total hours of existing music datasets come from non-Western genres.
  arXiv  Detail & Related papers  (2025-02-11T07:46:29Z)
• MuPT: A Generative Symbolic Music Pretrained Transformer [56.09299510129221]
  We explore the application of Large Language Models (LLMs) to the pre-training of music. To address the challenges associated with misaligned measures from different tracks during generation, we propose a Synchronized Multi-Track ABC Notation (SMT-ABC Notation) Our contributions include a series of models capable of handling up to 8192 tokens, covering 90% of the symbolic music data in our training set.
  arXiv  Detail & Related papers  (2024-04-09T15:35:52Z)
• Quantifying the evolution of harmony and novelty in western classical music [1.0152838128195467]
  We present a study of musical features related to harmony, and we document how they evolved over 400 years in western classical music. We develop measures to quantify key uncertainty, and diversity and novelty in key transitions. We report a decline in innovation in harmonic transitions in the early classical period followed by a steep increase in the late classical.
  arXiv  Detail & Related papers  (2023-08-06T23:00:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.