Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models

arXiv:2310.04743v2 Announce Type: replace
Abstract: Chain-of-thought (CoT) prompting, which offers step-by-step problem-solving rationales, has impressively unlocked the reasoning potential of large language models (LLMs). Yet, the standard CoT is less effective in problems demanding multiple reasoning steps. This limitation arises from the complex reasoning process in multi-step problems: later stages often depend on the results of several steps earlier, not just the results of the immediately preceding step. Such complexities suggest the reasoning process is naturally represented as a graph. …

abstract advances arxiv cs.cl language language models large language large language models llms multiple problem-solving process prompting reasoning residual standard step-by-step thought type unlocked