Leveraging Large Language Models to Generate Answer Set Programs
This work addresses the challenge of making formal logic accessible to non-experts by leveraging LLMs to assist in program creation, though it is incremental as it builds on existing neuro-symbolic approaches.
The paper tackles the problem of translating natural language descriptions of logic puzzles into formal answer set programs by proposing a neuro-symbolic method that uses large language models (LLMs) to generate these programs with few in-context examples, resulting in reasonably complex programs where most errors are simple and easily correctable by humans.
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.