SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
This addresses the issue of error detection in LLM reasoning for users relying on automated problem-solving, though it is incremental as it builds on existing chain-of-thought methods.
The paper tackles the problem of large language models making mistakes in complex step-by-step reasoning by proposing SelfCheck, a zero-shot verification schema that enables models to recognize their own errors without external resources, resulting in improved question-answering accuracies on datasets like GSM8K, MathQA, and MATH.
The recent progress in large language models (LLMs), especially the invention of chain-of-thought prompting, has made it possible to automatically answer questions by stepwise reasoning. However, when faced with more complicated problems that require non-linear thinking, even the strongest LLMs make mistakes. To address this, we explore whether LLMs are able to recognize errors in their own step-by-step reasoning, without resorting to external resources. To this end, we propose SelfCheck, a general-purpose zero-shot verification schema for recognizing such errors. We then use the results of these checks to improve question-answering performance by conducting weighted voting on multiple solutions to the question. We test SelfCheck on three datasets (GSM8K, MathQA, and MATH) and find that it successfully recognizes errors and, in turn, increases final answer accuracies.