Abstract
Large Language Models are a great tool for solving diverse tasks formulated in natural language. Recent work has demonstrated their capacity of solving tasks related to Knowledge Graphs, such as Knowledge Graph Completion or Knowledge Graph Reasoning, even in Zero- or Few-Shot paradigms. However, given a particular input, they do not always produce the same output, and sometimes point to intermediate reasoning steps that are not valid, even if they produce a satisfactorily answer. Moreover, the use of LLMs is mostly studied for static knowledge graphs, while temporal ones are overlooked. To highlight opportunities and challenges in knowledge graph related tasks, we experiment with ChatGPT on graph completion and reasoning for both static and temporal facets, using three different prompting techniques in Zero- and One-Shot contexts, on a Task-Oriented Dialogue system use case. Our results show that ChatGPT can solve given tasks, but mostly in a non-deterministic way.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
Fill, H., Fettke, P., Köpke, J.: Conceptual modeling and large language models: impressions from first experiments with ChatGPT. Enterp. Model. Inf. Syst. Archit. Int. J. Concept. Model. 18, 3 (2023). https://doi.org/10.18417/EMISA.18.3
Han, J., Collier, N., Buntine, W.L., Shareghi, E.: PiVe: prompting with iterative verification improving graph-based generative capability of LLMs. CoRR abs/2305.12392 (2023). https://doi.org/10.48550/ARXIV.2305.12392
Hogan, A., et al.: Knowledge Graphs. Synthesis Lectures on Data, Semantics, and Knowledge. Morgan & Claypool Publishers (2021). https://doi.org/10.2200/S01125ED1V01Y202109DSK022
Iga, V.I., Silaghi, G.C.: Leveraging BERT for natural language understanding of domain-specific knowledge. In: 25th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2023, Nancy, France. IEEE (2023, to appear)
Iga, V.I., Silaghi, G.C.: Ontology-based dialogue system for domain-specific knowledge acquisition. In: da Silva, A.R., et al. (ed.) ISD2023 Proceedings, Lisbon, Portugal. AIS (2023). https://doi.org/10.62036/ISD.2023.46
Ji, S., Pan, S., Cambria, E., Marttinen, P., Yu, P.S.: A survey on knowledge graphs: representation, acquisition, and applications. IEEE Trans. Neural Netw. Learn. Syst. 33(2), 494–514 (2022). https://doi.org/10.1109/TNNLS.2021.3070843
Liang, K., et al.: A survey of knowledge graph reasoning on graph types: static, dynamic, and multimodal. CoRR abs/2212.05767 (2022). https://doi.org/10.48550/arXiv.2212.05767
Nguyen, V., Bodenreider, O., Sheth, A.P.: Don’t like RDF reification?: making statements about statements using singleton property. In: Chung, C.-W., et al. (ed.) 23rd International WWW Conference, Seoul, Republic of Korea, pp. 759–770. ACM (2014). https://doi.org/10.1145/2566486.2567973
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying large language models and knowledge graphs: A roadmap. CoRR abs/2306.08302 (2023). https://doi.org/10.48550/ARXIV.2306.08302
Wang, J., et al.: A survey on temporal knowledge graph completion: taxonomy, progress, and prospects. CoRR abs/2308.02457 (2023). https://doi.org/10.48550/ARXIV.2308.02457
Wei, X., et al.: Zero-shot information extraction via chatting with chatgpt. CoRR abs/2302.10205 (2023). https://doi.org/10.48550/ARXIV.2302.10205
Zhang, J., Chen, B., Zhang, L., Ke, X., Ding, H.: Neural, symbolic and neural-symbolic reasoning on knowledge graphs. AI Open 2, 14–35 (2021). https://doi.org/10.1016/J.AIOPEN.2021.03.001
Zhao, W.X., et al.: A survey of large language models. CoRR abs/2303.18223 (2023). https://doi.org/10.48550/ARXIV.2303.18223
Zhu, Y., et al.: LLMs for knowledge graph construction and reasoning: recent capabilities and future opportunities. CoRR abs/2305.13168 (2023). https://doi.org/10.48550/ARXIV.2305.13168
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Iga, V.I.R., Silaghi, G.C. (2024). LLMs for Knowledge-Graphs Enhanced Task-Oriented Dialogue Systems: Challenges and Opportunities. In: Almeida, J.P.A., Di Ciccio, C., Kalloniatis, C. (eds) Advanced Information Systems Engineering Workshops. CAiSE 2024. Lecture Notes in Business Information Processing, vol 521. Springer, Cham. https://doi.org/10.1007/978-3-031-61003-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-61003-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-61002-8
Online ISBN: 978-3-031-61003-5
eBook Packages: Computer ScienceComputer Science (R0)