KGMistral: Towards Boosting the Performance of Large Language Models for Question Answering with Knowledge Graph Integration
Published in In Workshop on Deep Learning and Large Language Models for Knowledge Graphs., 2024
Recommended citation: Li, M., Yang, H., Liu, Z., Alam, M. M., Sack, H., & Gesese, G. A. (2024). KGMistral: Towards Boosting the Performance of Large Language Models for Question Answering with Knowledge Graph Integration. In Workshop on Deep Learning and Large Language Models for Knowledge Graphs.
In this paper, a novel question-answering (QA) approach named KGMistral is proposed, based on the Retrieval Augmented Generation (RAG) framework. Given the limitations of Large Language Models (LLMs) in generating accurate answers for domains not adequately covered by their training corpus, this work focuses on leveraging external domain-specific Knowledge Graphs (KGs) to enhance the performance of LLMs. Specifically, the study examines the benefits of using information from a KG to improve the QA performance of the Mistral model in the material science and engineering field. Experimental results indicate that KGMistral significantly enhances Mistral’s QA performance.
Recommended citation: Li, M., Yang, H., Liu, Z., Alam, M. M., Sack, H., & Gesese, G. A. (2024). KGMistral: Towards Boosting the Performance of Large Language Models for Question Answering with Knowledge Graph Integration. In Workshop on Deep Learning and Large Language Models for Knowledge Graphs.