Prompt optimization for frozen LLMs is formulated as KL-regularized reward maximization, and the alignment gap to RLHF is bounded by total-variation terms minus a KL term.
Fine-Tuning Language Models from Human Preferences
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
Prompt optimization for frozen LLMs is formulated as KL-regularized reward maximization, and the alignment gap to RLHF is bounded by total-variation terms minus a KL term.