Who cites «LLMs cannot find reasoning errors, but can correct them given the error location»
- Training Language Models to Self-Correct via Reinforcement LearningarXiv:2409.12917Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, et al.2024 · 151 citations
When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMsTransactions of the Association for Computational Linguistics (TACL)Ryo Kamoi, Yusen Zhang, Nan Zhang, et al.2024 · 159 citations
This page in Markdown → https://md.research.elamur.ai/free/en/papers/tyen-2024-llms-cannot-find-reasoning-errors/cited-by/