Integrating KGs and ontologies with RAG for personalised summarisation in regulatory compliance.

Arshad, Umair; Corsar, David; Nkisi-Orji, Ikechukwu

Abstract

With the growing complexity and increased volumes, regulatory texts are fast becoming a significant challenge for organisations to remain compliant. Traditional ways of summarising legal texts need to be more accommodating of critical, domain-specific requirements, rendering the process ultimately inefficient and subject to the risk of noncompliance. Therefore, this paper proposes a new solution integrating Ontology and Knowledge Graphs (KGs) with the Retrieval-Augmented Generation (RAG) paradigm to aid process automation and improve regulatory compliance. It offers deep semantic understanding, accurate contextual summaries, and personalised insights relevant to users' needs. In the meantime, this will assist organisations in operating with more precision and confidence in an ever-changing regulatory environment.

Citation

ARSHAD, U., CORSAR, D. and NKISI-ORJI, I. 2024. Integrating KGs and ontologies with RAG for personalised summarisation in regulatory compliance. In Martin, K., Salimi, P. and Wijayasekara, V. (eds.) 2024. SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822. Aachen: CEUR-WS [online], pages 56-61. Available from: https://ceur-ws.org/Vol-3822/short7.pdf

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2024 SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024)
• Start Date: Oct 17, 2024
• Acceptance Date: Oct 1, 2024
• Online Publication Date: Oct 17, 2024
• Publication Date: Nov 4, 2024
• Deposit Date: Dec 5, 2024
• Publicly Available Date: Dec 5, 2024
• Publisher: CEUR-WS
• Peer Reviewed: Peer Reviewed
• Pages: 56-61
• Series Title: CEUR-workshop proceedings
• Series Number: 3822
• Series ISSN: 1613-0073
• Keywords: Regulatory compliance; Knowledge graphs (KGs); Retrieval-augmented generation (RAG); Personalised summarisation
• Public URL: https://rgu-repository.worktribe.com/output/2613551
• Publisher URL: https://ceur-ws.org/Vol-3822/