A frozen 7B-8B LLM with a JSON rubric and a small LoRA adapter is claimed to outperform 27B-70B reward models and enable 92% GSM-8K exact match under online PPO.
Each category of algorithms presents unique benefits and constraints, rendering their integrated application beneficial in real -world scenarios
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
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art Performance
A frozen 7B-8B LLM with a JSON rubric and a small LoRA adapter is claimed to outperform 27B-70B reward models and enable 92% GSM-8K exact match under online PPO.