ChatLogic: Integrating Logic Programming with Large Language Models for Multi-Step Reasoning

TL;DR

ChatLogic enhances large language models' multi-step reasoning by integrating logic programming and symbolic memory, significantly improving deductive reasoning capabilities in complex tasks.

Contribution

This paper introduces ChatLogic, a novel framework that combines logic programming with LLMs to improve multi-step reasoning performance.

Findings

Significant improvement in multi-step reasoning accuracy.

Effective integration of symbolic memory with LLMs.

Open-source code and data available for replication.

Abstract

Large language models (LLMs) such as ChatGPT and GPT-4 have demonstrated impressive capabilities in various generative tasks. However, their performance is often hampered by limitations in accessing and leveraging long-term memory, leading to specific vulnerabilities and biases, especially during long interactions. This paper introduces ChatLogic, an innovative framework specifically targeted at LLM reasoning tasks that can enhance the performance of LLMs in multi-step deductive reasoning tasks by integrating logic programming. In ChatLogic, the language model plays a central role, acting as a controller and participating in every system operation stage. We propose a novel method of converting logic problems into symbolic integration with an inference engine. This approach leverages large language models' situational understanding and imitation skills and uses symbolic memory to enhance multi-step deductive reasoning capabilities. Our results show that the ChatLogic framework significantly improves the multi-step reasoning capabilities of LLMs. The source code and data are available at \url{https://github.com/Strong-AI-Lab/ChatLogic}