1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering

Jebish Purbey, Drishti Sharma, Siddhant Gupta, Khawaja Murad, Siddartha Pullakhandam, Ram Mohan Rao Kadiyala


Abstract
This paper presents the system description of our entry for the COLING 2025 RegNLP RIRAG (Regulatory Information Retrieval and Answer Generation) challenge, focusing on leveraging advanced information retrieval and answer generation techniques in regulatory domains. We experimented with a combination of embedding models, including Stella, BGE, CDE, and Mpnet, and leveraged fine-tuning and reranking for retrieving relevant documents in top ranks. We utilized a novel approach, LeSeR, which achieved competitive results with a recall@10 of 0.8201 and map@10 of 0.6655 for retrievals. This work highlights the transformative potential of natural language processing techniques in regulatory applications, offering insights into their capabilities for implementing a retrieval augmented generation system while identifying areas for future improvement in robustness and domain adaptation.
Anthology ID:
2025.regnlp-1.6
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:
36–40
Language:
URL:
https://aclanthology.org/2025.regnlp-1.6/
DOI:
Bibkey:
Cite (ACL):
Jebish Purbey, Drishti Sharma, Siddhant Gupta, Khawaja Murad, Siddartha Pullakhandam, and Ram Mohan Rao Kadiyala. 2025. 1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering. In Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025), pages 36–40, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering (Purbey et al., RegNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.regnlp-1.6.pdf