{"type":"ScholarlyArticle","title":"Integrating Answer Set Programming and Large Language Models for Enhanced Structured Representation of Complex Knowledge in Natural Language","authors":[{"name":"Mario Alviano","slug":"mario-alviano","given":"Mario","family":"Alviano","affiliation":""},{"name":"Lorenzo Grillo","slug":"lorenzo-grillo","given":"Lorenzo","family":"Grillo","affiliation":""},{"name":"Fabrizio Lo Scudo","slug":"fabrizio-lo-scudo","given":"Fabrizio","family":"Lo Scudo","affiliation":""},{"name":"Luis Angel Rodriguez Reiners","slug":"luis-angel-rodriguez-reiners","given":"Luis Angel","family":"Rodriguez Reiners","affiliation":""}],"abstract":"Answer Set Programming (ASP) and Large Language Models (LLMs) have emerged as powerful tools in Artificial Intelligence, each offering unique capabilities in knowledge representation and natural language processing, respectively. \r\nIn this paper, we combine the strengths of the two paradigms with the aim of improving the structured representation of complex knowledge encoded in natural language.\r\nIn a nutshell, the structured representation is obtained by combining syntactic structures extracted by LLMs and semantic aspects encoded in the knowledge base.\r\nThe interaction between ASP and LLMs is driven by a YAML file specifying prompt templates and domain-specific background knowledge. \r\nThe proposed approach is evaluated using a set of benchmarks based on a dataset obtained from problems of ASP Competitions.\r\nThe results of our experiment show that ASP can sensibly improve the F1-score, especially when relatively small models are used.","doi":"10.24963/ijcai.2025/482","url":"https://ijcai.org/proceedings/2025/482","pdf":"https://ijcai.org/proceedings/2025/0482.pdf","markdown":"https://ijcai.org/proceedings/2025/482.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/482","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":482,"pages":{"first":4330,"last":4338},"keywords":["Natural Language Processing: NLP: Information extraction","Knowledge Representation and Reasoning: KRR: Applications","Machine Learning: ML: Neuro-symbolic methods/Abductive Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}