{"ID":2888267,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23334","arxiv_id":"2507.23334","title":"MUST-RAG: MUSical Text Question Answering with Retrieval Augmented Generation","abstract":"Recent advancements in Large language models (LLMs) have demonstrated remarkable capabilities across diverse domains. While they exhibit strong zero-shot performance on various tasks, LLMs' effectiveness in music-related applications remains limited due to the relatively small proportion of music-specific knowledge in their training data. To address this limitation, we propose MusT-RAG, a comprehensive framework based on Retrieval Augmented Generation (RAG) to adapt general-purpose LLMs for text-only music question answering (MQA) tasks. RAG is a technique that provides external knowledge to LLMs by retrieving relevant context information when generating answers to questions. To optimize RAG for the music domain, we (1) propose MusWikiDB, a music-specialized vector database for the retrieval stage, and (2) utilizes context information during both inference and fine-tuning processes to effectively transform general-purpose LLMs into music-specific models. Our experiment demonstrates that MusT-RAG significantly outperforms traditional fine-tuning approaches in enhancing LLMs' music domain adaptation capabilities, showing consistent improvements across both in-domain and out-of-domain MQA benchmarks. Additionally, our MusWikiDB proves substantially more effective than general Wikipedia corpora, delivering superior performance and computational efficiency.","short_abstract":"Recent advancements in Large language models (LLMs) have demonstrated remarkable capabilities across diverse domains. While they exhibit strong zero-shot performance on various tasks, LLMs' effectiveness in music-related applications remains limited due to the relatively small proportion of music-specific knowledge in...","url_abs":"https://arxiv.org/abs/2507.23334","url_pdf":"https://arxiv.org/pdf/2507.23334v2","authors":"[\"Daeyong Kwon\",\"SeungHeon Doh\",\"Juhan Nam\"]","published":"2025-07-31T08:31:05Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.IR\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}