Abstract
Artificial Intelligence (AI) has been shown to productively affect organizational decision making, in terms of returned economic value. In particular, agile business may significantly benefit from the ability of AI systems to constantly pursue contextual knowledge awareness. Undoubtedly, a key added value of such systems is the ability to explain results. In fact, users are more inclined to trust and feel the accountability of systems, when the output is returned together with a human-readable explanation. Nevertheless, some of the information in an explanation might be irrelevant to users—despite its truthfulness. This paper discusses the relevance of explanation for resources similarity, provided by AI systems. In particular, the analysis focuses on one system based on Large Language Models (LLMs)—namely ChatGPT— and on one logic-based tool relying on the computation of the Least Common Subsumer in the Resource Description Framework (RDF). This discussion reveals the need for a formal distinction between relevant and irrelevant information, that we try to answer with a definition of relevance amenable to implementation.
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
- 1.
- 2.
Queried on December, 28th 2022.
- 3.
- 4.
The implementation at https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html has been used.
- 5.
References
Baader, F., Calvanese, D., McGuinness, D., Patel-Schneider, P., Nardi, D.: The Description Logic Handbook: Theory, Implementation and Applications. Cambridge University Press (2003)
Borlund, P.: The concept of relevance in IR. J. Am. Soc. Inf. Sci. Technol. 54(10), 913–925 (2003). https://onlinelibrary.wiley.com/doi/abs/10.1002/asi.10286
Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877–1901 (2020)
Colucci, S., Donini, F., Giannini, S., Di Sciascio, E.: Defining and computing least common subsumers in RDF. Web Semant. Sci. Serv. Agents World Wide Web 39, 62–80 (2016)
Colucci, S., Donini, F.M., Iurilli, N., Di Sciascio, E.: A business intelligence tool for explaining similarity. In: Babkin, E., Barjis, J., Malyzhenkov, P., Merunka, V. (eds.) Model-Driven Organizational and Business Agility - Second International Workshop, MOBA 2022, Leuven, Belgium, 6–7 June 2022, Revised Selected Papers. Lecture Notes in Business Information Processing, vol. 457, pp. 50–64. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-17728-6_5
Colucci, S., Donini, F.M., Di Sciascio, E.: Logical comparison over RDF resources in bio-informatics. J. Biomed. Informatics 76, 87–101 (2017). https://doi.org/10.1016/j.jbi.2017.11.004
Colucci, S., Di Noia, T., Di Sciascio, E., Donini, F.M., Ragone, A.: Semantic-based skill management for automated task assignment and courseware composition. J. Univers. Comput. Sci. 13(9), 1184–1212 (2007). https://doi.org/10.3217/jucs-013-09-1184
Colucci, S., Tinelli, E., Di Sciascio, E., Donini, F.M.: Automating competence management through non-standard reasoning. Eng. Appl. Artif. Intell. 24(8), 1368–1384 (2011). https://doi.org/10.1016/j.engappai.2011.05.015
Cooper, M.C., Marques-Silva, J.: Tractability of explaining classifier decisions. Artif. Intell. 316, 103841 (2023). https://www.sciencedirect.com/science/article/pii/S0004370222001813
Enholm, I.M., Papagiannidis, E., Mikalef, P., Krogstie, J.: Artificial intelligence and business value: a literature review. Inf. Syst. Front. 24(5), 1709–1734 (2022)
Hayes, P., Patel-Schneider, P.F.: RDF 1.1 semantics, W3C recommendation (2014). https://www.w3.org/TR/2014/REC-rdf11-mt-20140225/
Ignatiev, A.: Towards trustable explainable AI. In: IJCAI, pp. 5154–5158 (2020)
Jin, X., Han, J.: K-Means Clustering, pp. 563–564. Springer, Boston (2010). https://doi.org/10.1007/978-0-387-30164-8_425
Lakemeyer, G.: Relevance from an epistemic perspective. Artif. Intell. 97(1–2), 137–167 (1997). https://doi.org/10.1016/S0004-3702(97)00038-6
Lang, J., Liberatore, P., Marquis, P.: Propositional independence: formula-variable independence and forgetting. J. Artif. Intell. Res. 18, 391–443 (2003). https://doi.org/10.1613/jair.1113
Levy, A.Y., Fikes, R., Sagiv, Y.: Speeding up inferences using relevance reasoning: a formalism and algorithms. Artif. Intell. 97(1–2), 83–136 (1997). https://doi.org/10.1016/S0004-3702(97)00049-0
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019). https://www.sciencedirect.com/science/article/pii/S0004370218305988
OpenAI: ChatGPT: optimizing language models for dialogue. https://web.archive.org/web/20221130180912/openai.com/blog/chatgpt/. Accessed 18 Apr 2023
Schneider, J., Abraham, R., Meske, C., Brocke, J.V.: Artificial intelligence governance for businesses. Inf. Syst. Manag. 1–21 (2022)
Shadbolt, N., Hall, W., Berners-Lee, T.: The semantic web revisited. Intell. Syst. IEEE 21(3), 96–101 (2006)
Soylu, A., et al.: TheyBuyForYou platform and knowledge graph: expanding horizons in public procurement with open linked data. Semant. Web 13(2), 265–291 (2022)
Soylu, A., et al.: Towards an ontology for public procurement based on the open contracting data standard. In: Pappas, I.O., et al. (eds.) I3E 2019. LNCS, vol. 11701, pp. 230–237. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29374-1_19
Tinelli, E., Cascone, A., Ruta, M., Di Noia, T., Di Sciascio, E., Donini, F.M.: I.M.P.A.K.T.: an innovative semantic-based skill management system exploiting standard SQL. In: Cordeiro, J., Filipe, J. (eds.) ICEIS 2009 - Proceedings of the 11th International Conference on Enterprise Information Systems, Volume AIDSS, Milan, Italy, 6–10 May 2009, pp. 224–229 (2009)
Trunk, A., Birkel, H., Hartmann, E.: On the current state of combining human and artificial intelligence for strategic organizational decision making. Bus. Res. 13(3), 875–919 (2020)
Van Rijsbergen, C.: Information Retrieval (2nd edn). Butterworth-Heinemann, Newton (1979)
Van Rijsbergen, C.: Information retrieval: theory and practice. In: Proceedings of the joint IBM/University of Newcastle Upon Tyne Seminar on Data Base Systems, vol. 79 (1979)
Acknowledgements
Projects Regione Lazio-DTC/“SanLo” (CUP F85F21001090003) and Ministero dello Sviluppo Ecnoncomico/“Casa delle Tecnologie Emergenti dell’area metropolitana di Bari: Bari Open Innovation Hub” (CUP J99J19000300003) partially supported this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Colucci, S., Donini, F.M., Di Sciascio, E. (2023). On the Relevance of Explanation for RDF Resources Similarity. In: Babkin, E., Barjis, J., Malyzhenkov, P., Merunka, V., Molhanec, M. (eds) Model-Driven Organizational and Business Agility. MOBA 2023. Lecture Notes in Business Information Processing, vol 488. Springer, Cham. https://doi.org/10.1007/978-3-031-45010-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-45010-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45009-9
Online ISBN: 978-3-031-45010-5
eBook Packages: Computer ScienceComputer Science (R0)