通过符号链式思维实现忠实逻辑推理
Faithful Logical Reasoning via Symbolic Chain-of-Thought
AI总结：
本文提出SymbCoT框架，将符号表达式和逻辑规则融入链式思维提示，以增强大语言模型的逻辑推理能力，在多个标准数据集上取得最先进性能并提升推理的忠实性与可解释性。
摘要：
尽管最近的链式思维（CoT）技术借助心智理论增强了大语言模型（LLMs）的推理能力，但它在处理高度依赖符号表达式和严格演绎规则的逻辑推理时可能仍然存在困难。为了增强LLMs的逻辑推理能力，我们提出了一种新颖的符号链式思维，即SymbCoT，这是一个完全基于LLM的框架，将符号表达式和逻辑规则与CoT提示相结合。在技术实现上，基于一个LLM，SymbCoT 1）首先将自然语言上下文转换为符号格式，然后2）推导出逐步计划，利用符号逻辑规则解决问题，3）随后由一个验证器检查翻译和推理链。通过在5个标准数据集上使用一阶逻辑和约束优化符号表达式进行充分评估，SymbCoT始终展现出相对于CoT方法的显著改进，同时刷新了当前最先进的性能。我们进一步证明，我们的系统在更忠实、灵活和可解释的逻辑推理方面取得了进步。据我们所知，这是首次将符号表达式和规则结合到CoT中，用于LLM的逻辑推理。代码已在 https://github.com/Aiden0526/SymbCoT 开源。
英文摘要：
While the recent Chain-of-Thought (CoT) technique enhances the reasoning ability of large language models (LLMs) with the theory of mind, it might still struggle in handling logical reasoning that relies much on symbolic expressions and rigid deducing rules. To strengthen the logical reasoning capability of LLMs, we propose a novel Symbolic Chain-of-Thought, namely SymbCoT, a fully LLM-based framework that integrates symbolic expressions and logic rules with CoT prompting. Technically, building upon an LLM, SymbCoT 1) first translates the natural language context into the symbolic format, and then 2) derives a step-by-step plan to solve the problem with symbolic logical rules, 3) followed by a verifier to check the translation and reasoning chain. Via thorough evaluations on 5 standard datasets with both First-Order Logic and Constraint Optimization symbolic expressions, SymbCoT shows striking improvements over the CoT method consistently, meanwhile refreshing the current state-of-the-art performances. We further demonstrate that our system advances in more faithful, flexible, and explainable logical reasoning. To our knowledge, this is the first to combine symbolic expressions and rules into CoT for logical reasoning with LLMs. Code is open at https://github.com/Aiden0526/SymbCoT.
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。
