Question Answering with LLMs and Learning from Answer Sets
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- MindMap: Constructing Evidence Chains for Multi-Step Reasoning in Large Language ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text2023
- Inductive Logic Programming At 30: A New IntroductionJournal of Artificial Intelligence Research, 2022
- The Third AI Summer: AAAI Robert S. Engelmore Memorial LectureAI Magazine, 2022
- Addressing a Question Answering Challenge by Combining Statistical Methods with Inductive Rule Learning and ReasoningProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Commonsense reasoning and commonsense knowledge in artificial intelligenceCommunications of the ACM, 2015
- Incremental learning of event definitions with Inductive Logic ProgrammingMachine Learning, 2015
- Answer set programming at a glanceCommunications of the ACM, 2011
- Nonmonotonic abductive inductive learningJournal of Applied Logic, 2009
- A logic-based calculus of eventsNew Generation Computing, 1986