RIRAG: A Bi-Directional Retrieval-Enhanced Framework for Financial Legal QA in ObliQA Shared Task

Xinyan Zhang, Xiaobing Feng, Xiujuan Xu, Zhiliang Zheng, Kai Wu


Abstract
In professional financial-legal consulting services, accurately and efficiently retrieving and answering legal questions is crucial. Although some breakthroughs have been made in information retrieval and answer generation, few frameworks have successfully integrated these tasks. Therefore, we propose RIRAG (Retrieval-In-the-loop Response and Answer Generation), a bi-directional retrieval-enhanced framework for financial-legal question answering in ObliQA Shared Task. The system introduces BDD-FinLegal, which means Bi-Directional Dynamic finance-legal, a novel retrieval mechanism specifically designed for financial-legal documents, combining traditional retrieval algorithms with modern neural network methods. Legal answer generation is implemented through large language models retrained on expert-annotated datasets. Our method significantly improves the professionalism and interpretability of the answers while maintaining high retrieval accuracy. Experiments on the ADGM dataset show that the system achieved a significant improvement in the Recall@10 evaluation metric and was recognized by financial legal experts for the accuracy and professionalism of the answer generation. This study provides new ideas for building efficient and reliable question-answering systems in the financial-legal domain.
Anthology ID:
2025.regnlp-1.17
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:
107–113
Language:
URL:
https://aclanthology.org/2025.regnlp-1.17/
DOI:
Bibkey:
Cite (ACL):
Xinyan Zhang, Xiaobing Feng, Xiujuan Xu, Zhiliang Zheng, and Kai Wu. 2025. RIRAG: A Bi-Directional Retrieval-Enhanced Framework for Financial Legal QA in ObliQA Shared Task. In Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025), pages 107–113, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
RIRAG: A Bi-Directional Retrieval-Enhanced Framework for Financial Legal QA in ObliQA Shared Task (Zhang et al., RegNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.regnlp-1.17.pdf