Question Answering with LLMs and Learning from Answer Sets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Borroto, Manuel, Gallagher, Katie, Ielo, Antonio, Kareem, Irfan, Ricca, Francesco, Russo, Alessandra
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912595906134016
author Borroto, Manuel
Gallagher, Katie
Ielo, Antonio
Kareem, Irfan
Ricca, Francesco
Russo, Alessandra
author_facet Borroto, Manuel
Gallagher, Katie
Ielo, Antonio
Kareem, Irfan
Ricca, Francesco
Russo, Alessandra
contents Large Language Models (LLMs) excel at understanding natural language but struggle with explicit commonsense reasoning. A recent trend of research suggests that the combination of LLM with robust symbolic reasoning systems can overcome this problem on story-based question answering tasks. In this setting, existing approaches typically depend on human expertise to manually craft the symbolic component. We argue, however, that this component can also be automatically learned from examples. In this work, we introduce LLM2LAS, a hybrid system that effectively combines the natural language understanding capabilities of LLMs, the rule induction power of the Learning from Answer Sets (LAS) system ILASP, and the formal reasoning strengths of Answer Set Programming (ASP). LLMs are used to extract semantic structures from text, which ILASP then transforms into interpretable logic rules. These rules allow an ASP solver to perform precise and consistent reasoning, enabling correct answers to previously unseen questions. Empirical results outline the strengths and weaknesses of our automatic approach for learning and reasoning in a story-based question answering benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16590
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Question Answering with LLMs and Learning from Answer Sets
Borroto, Manuel
Gallagher, Katie
Ielo, Antonio
Kareem, Irfan
Ricca, Francesco
Russo, Alessandra
Artificial Intelligence
Computation and Language
Logic in Computer Science
Large Language Models (LLMs) excel at understanding natural language but struggle with explicit commonsense reasoning. A recent trend of research suggests that the combination of LLM with robust symbolic reasoning systems can overcome this problem on story-based question answering tasks. In this setting, existing approaches typically depend on human expertise to manually craft the symbolic component. We argue, however, that this component can also be automatically learned from examples. In this work, we introduce LLM2LAS, a hybrid system that effectively combines the natural language understanding capabilities of LLMs, the rule induction power of the Learning from Answer Sets (LAS) system ILASP, and the formal reasoning strengths of Answer Set Programming (ASP). LLMs are used to extract semantic structures from text, which ILASP then transforms into interpretable logic rules. These rules allow an ASP solver to perform precise and consistent reasoning, enabling correct answers to previously unseen questions. Empirical results outline the strengths and weaknesses of our automatic approach for learning and reasoning in a story-based question answering benchmark.
title Question Answering with LLMs and Learning from Answer Sets
topic Artificial Intelligence
Computation and Language
Logic in Computer Science
url https://arxiv.org/abs/2509.16590