Forcing a self-rewarding LLM's generative judge and implicit DPO reward to agree on preference labels substantially improves its AlpacaEval 2.0 alignment score.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models
Forcing a self-rewarding LLM's generative judge and implicit DPO reward to agree on preference labels substantially improves its AlpacaEval 2.0 alignment score.