推理链的演绎验证

Deductive Verification of Chain-of-Thought Reasoning

June 6, 2023

作者: Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, Hao Su

cs.AI

摘要

大型语言模型（LLMs）在执行各种推理任务时，显著受益于“Chain-of-Thought”（CoT）提示。虽然CoT允许模型生成更全面的推理过程，但其强调中间推理步骤可能会无意中引入幻觉和累积错误，从而限制模型解决复杂推理任务的能力。受人类如何进行谨慎细致的演绎逻辑推理过程以解决任务的启发，我们致力于使语言模型能够执行明确严谨的演绎推理，并通过自我验证确保推理过程的可信性。然而，即使使用像ChatGPT这样的先进模型，直接验证整个演绎推理过程的有效性也是具有挑战性的。鉴于此，我们提议将推理验证过程分解为一系列逐步子过程，每个子过程仅接收其必要的上下文和前提。为了促进这一过程，我们提出了“自然程序”（Natural Program），这是一种基于自然语言的演绎推理格式。我们的方法使模型能够生成精确的推理步骤，其中后续步骤更严谨地建立在前期步骤之上。它还赋予语言模型以逐步方式进行推理自我验证的能力。通过将这一验证过程整合到每个演绎推理阶段中，我们显著增强了生成推理步骤的严谨性和可信度。在这一过程中，我们还提高了对复杂推理任务的答案正确性。代码将在https://github.com/lz1oceani/verify_cot上发布。

English

Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive reasoning processes, its emphasis on intermediate reasoning steps can inadvertently introduce hallucinations and accumulated errors, thereby limiting models' ability to solve complex reasoning tasks. Inspired by how humans engage in careful and meticulous deductive logical reasoning processes to solve tasks, we seek to enable language models to perform explicit and rigorous deductive reasoning, and also ensure the trustworthiness of their reasoning process through self-verification. However, directly verifying the validity of an entire deductive reasoning process is challenging, even with advanced models like ChatGPT. In light of this, we propose to decompose a reasoning verification process into a series of step-by-step subprocesses, each only receiving their necessary context and premises. To facilitate this procedure, we propose Natural Program, a natural language-based deductive reasoning format. Our approach enables models to generate precise reasoning steps where subsequent steps are more rigorously grounded on prior steps. It also empowers language models to carry out reasoning self-verification in a step-by-step manner. By integrating this verification process into each deductive reasoning stage, we significantly enhance the rigor and trustfulness of generated reasoning steps. Along this process, we also improve the answer correctness on complex reasoning tasks. Code will be released at https://github.com/lz1oceani/verify_cot.