Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning

arXiv:2403.20046v1 Announce Type: new
Abstract: Recent works have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought (CoT) rationales or using them as correct examples in few-shot prompting. While humans can indeed imitate correct examples, learning from our mistakes is another vital aspect of human cognition. Hence, a question naturally arises: \textit{can LLMs learn and benefit from their mistakes, especially for their reasoning? } This study investigates this problem from both the prompting and model-tuning perspectives. We begin by introducing …

abstract arxiv benefits boost cognition cs.cl errors examples few-shot fine-tuning human humans indeed learn llms mistakes prompting reasoning standard them thought type vital