Verifying Reasoning Chains Generated by Large Language Models: A Survey

Large Language Models (LLMs) are extensively used for many Natural Language Processing tasks such as question answering, natural language inference, document summarization, etc. Chain-of-Thought (CoT) prompting compels LLMs to generate step-by-step reasoning chains. While some of the reasoning chains may follow a correct thought process, they can also suffer from hallucinations, leading to errors in answer generation. Recently, many articles have targeted the problem of verifying these reasoning chains from various aspects. Despite this recent attention, to the best of our knowledge, no comprehensive survey currently summarizes these studies on reasoning chain verification. This work addresses that gap by presenting a detailed overview of the methods for verifying reasoning chains and categorizing them according to their methodology. This paper introduces a novel taxonomy of existing reasoning chain verification methods and mainly divides them into approaches that assess entire chains versus those that examine individual steps. This paper also reviews benchmarks for evaluating reasoning chains and verification methods and further discusses the challenges and future directions associated with these methods. By compiling and analyzing these approaches, our survey aims to advance the understanding and development of robust reasoning techniques in LLMs.