Performance Comparison of MusT-RAG and Text-Only RAG on Music-Related QA Tasks

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 L

Research goal: How does the performance of MusT-RAG compare to text-only RAG on music-related QA tasks when evaluated using specialized music benchmarks like MusiQA or AudioSet across different model sizes (7B vs. 70B)?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 9.2/10.