RLSC, a method that uses a language model's self-confidence as reward, is shown to improve math benchmark accuracy, but the results are undermined by training on the AIME test set and the method reduces to known self-distillation.
Evalchemy: Automatic evals for llms, 2024
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.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
RLSC, a method that uses a language model's self-confidence as reward, is shown to improve math benchmark accuracy, but the results are undermined by training on the AIME test set and the method reduces to known self-distillation.