用符号结构提升大模型逻辑推理的透明度和准确性。
Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoning
- 在提示中加入轻量符号表示，让推理过程更清晰。
- 在四个基准上均优于传统链式思考，三组表现显著提升。
- 适合需要可解释推理的复杂任务场景。
本文提出符号辅助链式思考（Symbolic-Aided CoT），一种改进的标准链式思考方法，用于大语言模型的逻辑推理。核心思想是在少样本提示中引入轻量级符号表示，以一致策略结构化推理步骤，使非交互式推理过程中的推理模式更加显式。通过整合这些符号结构，该方法在保持标准提示通用性的同时，提升了大模型逻辑推理的透明度、可解释性和可分析性。在四个知名逻辑推理基准——ProofWriter、FOLIO、ProntoQA 和 LogicalDeduction 上的广泛实验表明，该方法在需处理多重约束或规则的复杂推理任务中尤为有效。值得注意的是，符号辅助CoT在不同规模模型上均持续提升推理能力，并在三个数据集（ProofWriter、ProntoQA、LogicalDeduction）上显著优于传统CoT。
原文摘要 · Abstract (English)
This work introduces Symbolic-Aided Chain-of-Thought (CoT), an improved approach to standard CoT, for logical reasoning in large language models (LLMs). The key idea is to integrate lightweight symbolic representations into few-shot prompts, structuring the inference steps with a consistent strategy to make reasoning patterns more explicit within a non-interactive reasoning process. By incorporating these symbolic structures, Symbolic-Aided CoT preserves the generalizability of standard prompting techniques while enhancing the transparency, interpretability, and analyzability of LLM logical reasoning. Extensive experiments on four well-known logical reasoning benchmarks -- ProofWriter, FOLIO, ProntoQA, and LogicalDeduction, which cover diverse reasoning tasks and scenarios -- demonstrate the effectiveness of the proposed approach, particularly in complex reasoning tasks that require navigating multiple constraints or rules. Notably, Symbolic-Aided CoT consistently improves LLMs' reasoning capabilities across various model sizes and significantly outperforms conventional CoT on three out of four datasets, ProofWriter, ProntoQA, and LogicalDeduction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。