思维链推理的演绎验证
Deductive Verification of Chain-of-Thought Reasoning
AI总结：
针对大语言模型思维链推理易产生幻觉与累积误差的问题，本研究提出基于Natural Program格式的逐步演绎自验证方法，提升了推理严谨性与复杂任务答案准确率。
摘要：
大语言模型（LLM）在执行各类推理任务时能从思维链（Chain-of-Thought，CoT）提示中显著获益。尽管CoT能让模型生成更全面的推理过程，但其对中间推理步骤的侧重会意外引入幻觉和累积误差，进而限制模型解决复杂推理任务的能力。受人类通过严谨细致的演绎逻辑推理过程解决任务的方式启发，我们旨在让语言模型能够执行明确且严格的演绎推理，同时通过自验证确保其推理过程的可信度。然而，即便使用ChatGPT这类先进模型，直接验证整个演绎推理过程的有效性仍颇具挑战。鉴于此，我们提出将推理验证过程分解为一系列逐步执行的子过程，每个子过程仅接收其所需的上下文和前提。为推进这一流程，我们提出了Natural Program——一种基于自然语言的演绎推理格式。我们的方法让模型能够生成精确的推理步骤，使后续步骤更严格地建立在先前步骤的基础上，同时也让语言模型能够以逐步方式开展推理自验证。通过将这一验证过程整合到每个演绎推理阶段，我们显著提升了生成推理步骤的严谨性与可信度，在此过程中也提高了模型在复杂推理任务上的答案准确率。代码将发布于https://github.com/lz1oceani/verify_cot。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
