A closed-loop benchmark that scores LLM critiques by the correctness of the corrections they produce finds o1-mini clearly outperforms classical LLMs, which often get worse after self-critique.
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
-
RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques
A closed-loop benchmark that scores LLM critiques by the correctness of the corrections they produce finds o1-mini clearly outperforms classical LLMs, which often get worse after self-critique.