Domain Specific Question Answering Over Knowledge Graphs Using Logical Programming and Large Language Models
This work addresses the challenge of domain-specific question answering for users needing explainable and robust solutions, though it appears incremental as it combines existing methods (logical programming and LLMs) on a known dataset.
The paper tackles the problem of question answering over domain-specific knowledge graphs by integrating logical programming languages with large language models, achieving accurate identification of correct answer entities for all test questions on the MetaQA benchmark dataset, even with limited training data.
Answering questions over domain-specific graphs requires a tailored approach due to the limited number of relations and the specific nature of the domain. Our approach integrates classic logical programming languages into large language models (LLMs), enabling the utilization of logical reasoning capabilities to tackle the KGQA task. By representing the questions as Prolog queries, which are readable and near close to natural language in representation, we facilitate the generation of programmatically derived answers. To validate the effectiveness of our approach, we evaluate it using a well-known benchmark dataset, MetaQA. Our experimental results demonstrate that our method achieves accurate identification of correct answer entities for all test questions, even when trained on a small fraction of annotated data. Overall, our work presents a promising approach to addressing question answering over domain-specific graphs, offering an explainable and robust solution by incorporating logical programming languages.