Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoning
This addresses the problem of enhancing logical reasoning capabilities in LLMs for researchers and practitioners, representing an incremental improvement over existing methods.
This work tackled the problem of improving logical reasoning in large language models by introducing Symbolic-Aided Chain-of-Thought, which integrates symbolic representations into prompts to enhance transparency and interpretability. The result showed consistent improvements across model sizes and outperformed conventional CoT on three out of four datasets, including ProofWriter, ProntoQA, and LogicalDeduction.
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.