Large Language Models are Better Reasoners with Self-Verification
Citations Over TimeTop 1% of 2023 papers
Abstract
Recently, with the chain of thought (CoT) prompting, large language models (LLMs), e.g., GPT-3, have shown strong reasoning ability in several natural language processing tasks such as arithmetic, commonsense, and logical reasoning. However, LLMs with CoT require multi-step prompting and multi-token prediction, which is highly sensitive to individual mistakes and vulnerable to error accumulation. The above issues make the LLMs need the ability to verify the answers. In fact, after inferring conclusions in some thinking decision tasks, people often check them by re-verifying steps to avoid some mistakes. In this paper, we propose and prove that LLMs also have similar self-verification abilities. We take the conclusion obtained by CoT as one of the conditions for solving the original problem. By performing a backward verification of the answers that LLM deduced for itself, we can obtain interpretable answer validation scores to select the candidate answer with the highest score. Experimental results demonstrate that the proposed method can improve the reasoning performance on various arithmetic, commonsense, and logical reasoning datasets. Our code is publicly available at: https://github.com/WENGSYX/Self-Verification.
Related Papers
- → Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning(2020)46 cited
- Tackling Benchmark Problems of Commonsense Reasoning.(2015)
- Discussion on Induction and Deduction in Science Inquiry(2006)
- Discussion of Analogy Reasoning(2003)