Integrating Answer Set Programming and Large Language Models for Enhanced Structured Representation of Complex Knowledge in Natural Language

Alviano, Mario; Grillo, Lorenzo; Lo Scudo, Fabrizio; Rodriguez Reiners, Luis Angel

doi:10.24963/ijcai.2025/482

Integrating Answer Set Programming and Large Language Models for Enhanced Structured Representation of Complex Knowledge in Natural Language

Mario Alviano, Lorenzo Grillo, Fabrizio Lo Scudo, Luis Angel Rodriguez Reiners

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 4330-4338.

https://doi.org/10.24963/ijcai.2025/482

Keywords

Natural Language Processing: NLP: Information extraction
Knowledge Representation and Reasoning: KRR: Applications
Machine Learning: ML: Neuro-symbolic methods/Abductive Learning

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.

In 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.

In a nutshell, the structured representation is obtained by combining syntactic structures extracted by LLMs and semantic aspects encoded in the knowledge base.

The interaction between ASP and LLMs is driven by a YAML file specifying prompt templates and domain-specific background knowledge.

The proposed approach is evaluated using a set of benchmarks based on a dataset obtained from problems of ASP Competitions.

The results of our experiment show that ASP can sensibly improve the F1-score, especially when relatively small models are used.

Mario Alviano, Lorenzo Grillo, Fabrizio Lo Scudo, and Luis Angel Rodriguez Reiners. 2025. Integrating Answer Set Programming and Large Language Models for Enhanced Structured Representation of Complex Knowledge in Natural Language. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 4330–4338. https://doi.org/10.24963/ijcai.2025/482

@inproceedings{ijcai2025p482,
  title     = {Integrating Answer Set Programming and Large Language Models for Enhanced Structured Representation of Complex Knowledge in Natural Language},
  author    = {Alviano, Mario and Grillo, Lorenzo and Lo Scudo, Fabrizio and Rodriguez Reiners, Luis Angel},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {4330--4338},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/482},
  url       = {https://doi.org/10.24963/ijcai.2025/482},
}

TY  - CPAPER
TI  - Integrating Answer Set Programming and Large Language Models for Enhanced Structured Representation of Complex Knowledge in Natural Language
AU  - Alviano, Mario
AU  - Grillo, Lorenzo
AU  - Lo Scudo, Fabrizio
AU  - Rodriguez Reiners, Luis Angel
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 4330
EP  - 4338
DO  - 10.24963/ijcai.2025/482
UR  - https://doi.org/10.24963/ijcai.2025/482
ER  -