RAGulator: Effective RAG for Regulatory Question Answering

Islam Aushev, Egor Kratkov, Evgenii Nikoalev, Andrei Vladimirovich Glinskii, Vasilii Krikunov, Alexander Panchenko, Vasily Konovalov, Julia Belikova


Abstract
Regulatory Natural Language Processing (RegNLP) is a multidisciplinary domain focused on facilitating access to and comprehension of regulatory regulations and requirements. This paper outlines our strategy for creating a system to address the Regulatory Information Retrieval and Answer Generation (RIRAG) challenge, which was conducted during the RegNLP 2025 Workshop. The objective of this competition is to design a system capable of efficiently extracting pertinent passages from regulatory texts (ObliQA) and subsequently generating accurate, cohesive responses to inquiries related to compliance and obligations. Our proposed method employs a lightweight BM25 pre-filtering in retrieving relevant passages. This technique efficiently shortlisting candidates for subsequent processing with Transformer-based embeddings, thereby optimizing the use of resources.
Anthology ID:
2025.regnlp-1.18
Volume:
Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Tuba Gokhan, Kexin Wang, Iryna Gurevych, Ted Briscoe
Venues:
RegNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
114–120
Language:
URL:
https://aclanthology.org/2025.regnlp-1.18/
DOI:
Bibkey:
Cite (ACL):
Islam Aushev, Egor Kratkov, Evgenii Nikoalev, Andrei Vladimirovich Glinskii, Vasilii Krikunov, Alexander Panchenko, Vasily Konovalov, and Julia Belikova. 2025. RAGulator: Effective RAG for Regulatory Question Answering. In Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025), pages 114–120, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
RAGulator: Effective RAG for Regulatory Question Answering (Aushev et al., RegNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.regnlp-1.18.pdf