Cross-Domain Fine-Tuning with RAG Enhances Llama-3-8B Robustness in Music QA Benchmarks

This report synthesises findings from 13 peer-reviewed papers addressing the following research question: Can cross-domain fine-tuning of Llama-3-8B with RAG improve its robustness on music QA benchmarks compared to domain-specific fine-tuning, as measured by accuracy and generalization scores. Long-Context Question Answering (LCQA), a challenging task, aims to reason over longcontext documents to yield accurate answers to questions.Existing long-context Large Language Models (LLMs) for LCQA often struggle with the "lost in the middle" issue.Retrieval-Augmented. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: Can cross-domain fine-tuning of Llama-3-8B with RAG improve its robustness on music QA benchmarks compared to domain-specific fine-tuning, as measured by accuracy and generalization scores?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.