Learning From Correctness Without Prompting Makes LLM Efficient Reasoner

arXiv:2403.19094v1 Announce Type: new
Abstract: Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content. One potential approach to mitigate these issues is learning from human or external feedback (e.g. tools). In this paper, we introduce an intrinsic self-correct reasoning framework for LLMs that eliminates the need for human feedback, external tools, and handcraft prompts. The proposed framework, based on a multi-step reasoning paradigm \textbf{Le}arning from …

abstract arxiv cs.cl feedback hallucination human language language models large language large language models limitations llm llms paper performance prompting reasoning tasks tools type