Rule-generated preference data aligned via sequential DPO and KTO reduces musical constraint violations and improves coherence in lyric-to-melody generation over baselines.
Training language models to follow instructions with human feedback,
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 Language Models for Lyric-to-Melody Generation with Rule-Based Musical Constraints
Rule-generated preference data aligned via sequential DPO and KTO reduces musical constraint violations and improves coherence in lyric-to-melody generation over baselines.