General Purpose Verification for Chain of Thought Prompting

arXiv:2405.00204v1 Announce Type: new
Abstract: Many of the recent capabilities demonstrated by Large Language Models (LLMs) arise primarily from their ability to exploit contextual information. In this paper, we explore ways to improve reasoning capabilities of LLMs through (1) exploration of different chains of thought and (2) validation of the individual steps of the reasoning process. We propose three general principles that a model should adhere to while reasoning: (i) Relevance, (ii) Mathematical Accuracy, and (iii) Logical Consistency. We apply …

abstract arxiv capabilities chain of thought cs.ai cs.cl exploit exploration explore general information language language models large language large language models llms paper prompting reasoning thought through type validation verification