KR2023Proceedings of the 20th International Conference on Principles of Knowledge Representation and ReasoningProceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning

Rhodes, Greece. September 2-8, 2023.

Edited by

ISSN: 2334-1033
ISBN: 978-1-956792-02-7

Sponsored by
Published by

Copyright © 2023 International Joint Conferences on Artificial Intelligence Organization

Leveraging Large Language Models to Generate Answer Set Programs

  1. Adam Ishay(Arizona State University)
  2. Zhun Yang(Arizona State University)
  3. Joohyung Lee(Arizona State University, Samsung Research)


  1. Integrating knowledge representation and machine learning
  2. KR and natural language processing and understanding
  3. Logic programming, answer set programming


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.