@article{ART003120924},
author={Min-Ji Seo and Myung-Ho Kim},
title={Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2024},
volume={29},
number={9},
pages={39-48},
doi={10.9708/jksci.2024.29.09.039}
TY - JOUR
AU - Min-Ji Seo
AU - Myung-Ho Kim
TI - Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models
JO - Journal of The Korea Society of Computer and Information
PY - 2024
VL - 29
IS - 9
PB - The Korean Society Of Computer And Information
SP - 39
EP - 48
SN - 1598-849X
AB - In this study, we propose a method to augment the provided reasoning paths to improve the answer performance and explanatory power of KGQA. In the proposed method, we utilize LLMs and GNNs to retrieve reasoning paths related to the question from the knowledge graph and evaluate reasoning paths.
Then, we retrieve the external information related to the question and then converted into triples to answer the question and explain the reason. Our method evaluates the reasoning path by checking inference results and semantically by itself. In addition, we find related texts to the question based on their similarity and converting them into triples of knowledge graph. We evaluated the performance of the proposed method using the WebQuestion Semantic Parsing dataset, and found that it provides correct answers with higher accuracy and more questions with explanations than the reasoning paths by the previous research.
KW - Knowledge Graph Question Answering;Self-evaluation;Large Language Models
DO - 10.9708/jksci.2024.29.09.039
ER -
Min-Ji Seo and Myung-Ho Kim. (2024). Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models. Journal of The Korea Society of Computer and Information, 29(9), 39-48.
Min-Ji Seo and Myung-Ho Kim. 2024, "Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models", Journal of The Korea Society of Computer and Information, vol.29, no.9 pp.39-48. Available from: doi:10.9708/jksci.2024.29.09.039
Min-Ji Seo, Myung-Ho Kim "Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models" Journal of The Korea Society of Computer and Information 29.9 pp.39-48 (2024) : 39.
Min-Ji Seo, Myung-Ho Kim. Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models. 2024; 29(9), 39-48. Available from: doi:10.9708/jksci.2024.29.09.039
Min-Ji Seo and Myung-Ho Kim. "Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models" Journal of The Korea Society of Computer and Information 29, no.9 (2024) : 39-48.doi: 10.9708/jksci.2024.29.09.039
Min-Ji Seo; Myung-Ho Kim. Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models. Journal of The Korea Society of Computer and Information, 29(9), 39-48. doi: 10.9708/jksci.2024.29.09.039
Min-Ji Seo; Myung-Ho Kim. Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models. Journal of The Korea Society of Computer and Information. 2024; 29(9) 39-48. doi: 10.9708/jksci.2024.29.09.039
Min-Ji Seo, Myung-Ho Kim. Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models. 2024; 29(9), 39-48. Available from: doi:10.9708/jksci.2024.29.09.039
Min-Ji Seo and Myung-Ho Kim. "Research on improving KGQA efficiency using self-enhancement of reasoning paths based on Large Language Models" Journal of The Korea Society of Computer and Information 29, no.9 (2024) : 39-48.doi: 10.9708/jksci.2024.29.09.039
