Feedback-driven alignment with numerical rewards improves MusicLLM emotion regression on arousal and valence over instruction tuning alone while preserving MusicQA performance.
CMI-Bench: A comprehensive bench- mark for evaluating music instruction following,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Aligning MusicLLM with Emotion using Instruction Tuning and Feedback-Driven Alignment
Feedback-driven alignment with numerical rewards improves MusicLLM emotion regression on arousal and valence over instruction tuning alone while preserving MusicQA performance.