Leveraging Large Language Models to Generate Answer Set Programs

TL;DR

This paper introduces a neuro-symbolic approach that uses large language models to convert natural language logic puzzles into answer set programs, combining NLP and formal logic for improved reasoning tasks.

Contribution

It demonstrates that LLMs can effectively generate answer set programs from natural language with minimal examples, bridging the gap between NLP and formal logic reasoning.

Findings

LLMs can generate complex answer set programs with few examples

Most errors are simple and human-correctable

The approach enhances reasoning capabilities of LLMs

Abstract

Large language models (LLMs), such as GPT-3 and GPT-4, have demonstrated exceptional performance in various natural language processing tasks and have shown the ability to solve certain reasoning problems. However, their reasoning capabilities are limited and relatively shallow, despite the application of various prompting techniques. In contrast, formal logic is adept at handling complex reasoning, but translating natural language descriptions into formal logic is a challenging task that non-experts struggle with. This paper proposes a neuro-symbolic method that combines the strengths of large language models and answer set programming. Specifically, we employ an LLM to transform natural language descriptions of logic puzzles into answer set programs. We carefully design prompts for an LLM to convert natural language descriptions into answer set programs in a step by step manner. Surprisingly, with just a few in-context learning examples, LLMs can generate reasonably complex answer set programs. The majority of errors made are relatively simple and can be easily corrected by humans, thus enabling LLMs to effectively assist in the creation of answer set programs.