DIVE combines global sample pooling with diversity-aware data selection to counter output diversity collapse in iterative preference learning for LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DIVE: Diversified Iterative Self-Improvement
DIVE combines global sample pooling with diversity-aware data selection to counter output diversity collapse in iterative preference learning for LLMs.