A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): models, evaluation metrics, benchmarks, and challenges

被引:1
作者
Ibrahim, Nourhan [1 ,2 ]
Aboulela, Samar [1 ]
Ibrahim, Ahmed [3 ]
Kashef, Rasha [1 ]
机构
[1] Electrical, Computer, and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON
[2] Faculty of Engineering, Alexandria University, Alexandria
[3] Computer Science, Western University, London, ON
来源
Discover Artificial Intelligence | 2024年 / 4卷 / 01期
关键词
Deep learning (DL); Evaluation metrics; Knowledge graphs (KGs); Large language models (LLMs); Retrieval augmentation generation (RAG);
D O I
10.1007/s44163-024-00175-8
中图分类号
学科分类号
摘要
Integrating Large Language Models (LLMs) with Knowledge Graphs (KGs) enhances the interpretability and performance of AI systems. This research comprehensively analyzes this integration, classifying approaches into three fundamental paradigms: KG-augmented LLMs, LLM-augmented KGs, and synergized frameworks. The evaluation examines each paradigm’s methodology, strengths, drawbacks, and practical applications in real-life scenarios. The findings highlight the substantial impact of these integrations in fundamentally improving real-time data analysis, efficient decision-making, and promoting innovation across various domains. In this paper, we also describe essential evaluation metrics and benchmarks for assessing the performance of these integrations, addressing challenges like scalability and computational overhead, and providing potential solutions. This comprehensive analysis underscores the profound impact of these integrations on improving real-time data analysis, enhancing decision-making efficiency, and fostering innovation across various domains. © The Author(s) 2024.
引用
收藏
相关论文
共 92 条
[1]  
Wang H., Xu Z., Fujita H., Liu S., Towards felicitous decision making: an overview on challenges and trends of big data, Inform Sci, 367, pp. 747-765, (2016)
[2]  
Hu H., Wen Y., Chua T.-S., Li X., Toward scalable systems for big data analytics: a technology tutorial, IEEE Access, 2, pp. 652-687, (2014)
[3]  
Yang J., Yao W., Zhang W., Keyword search on large graphs: a survey, Data Sci Eng, 6, 2, pp. 142-162, (2021)
[4]  
Yuan Y., Lian X., Chen L., Yu J.X., Wang G., Sun Y., Keyword search over distributed graphs with compressed signature, IEEE Trans Knowle Data Eng, 29, 6, pp. 1212-1225, (2017)
[5]  
Brown T.B., Language Models are Few-Shot Learners., (2020)
[6]  
Lee J., Toutanova K., . Pre-training of deep bidirectional transformers for language understanding.
[7]  
Jiang J., Huang X., Choi B., Xu J., Bhowmick S.S., Xu L., Ppkws: An efficient framework for keyword search on public-private networks, In: 2020 IEEE 36Th International Conference on Data Engineering (ICDE), (2020)
[8]  
Hogan A., Blomqvist E., Cochez M., d'Amato C., Melo G.D., Gutierrez C., Kirrane S., Gayo J.E.L., Navigli R., Neumaier S., Et al., Knowledge graphs, ACM Comput Surveys, 54, 4, pp. 1-37, (2021)
[9]  
Bollacker K., Evans C., Paritosh P., Sturge T., Taylor J., . Freebase: A collaboratively created graph database for structuring human knowledge, In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, (2008)
[10]  
Lully V., Laublet P., Stankovic M., Radulovic F., Enhancing explanations in recommender systems with knowledge graphs, Proc Comput Sci, 137, pp. 211-222, (2018)