NUST Omega at RIRAG 2025: Investigating Context-aware Retrieval and Answer Generations-Lessons and Challenges

Huma Ameer, Muhammad Hannan Akram, Seemab Latif, Mehwish Fatima


Abstract
NUST Omega participates in Regulatory Information Retrieval and Answer Generation (RIRAG) Shared Task. Regulatory documents poses unique challenges in retrieving and generating precise and relevant answers due to their inherent complexities. We explore the task by proposing a progressive retrieval pipeline and investigate its performance with multiple variants. Some variants include different embeddings to explore their effects on the retrieval score. Some variants examine the inclusion of keyword-driven query matching technique. After exploring such variations, we include topic modeling in our pipeline to investigate its impact on the performance. We also study the performance of various prompt techniques with our proposed pipeline. With empirical experiments, we find some strengths and limitations in the proposed pipeline. These findings will help the research community by offering valuable insights to make advancements in tackling this complex task.
Anthology ID:
2025.regnlp-1.13
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:
85–90
Language:
URL:
https://aclanthology.org/2025.regnlp-1.13/
DOI:
Bibkey:
Cite (ACL):
Huma Ameer, Muhammad Hannan Akram, Seemab Latif, and Mehwish Fatima. 2025. NUST Omega at RIRAG 2025: Investigating Context-aware Retrieval and Answer Generations-Lessons and Challenges. In Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025), pages 85–90, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
NUST Omega at RIRAG 2025: Investigating Context-aware Retrieval and Answer Generations-Lessons and Challenges (Ameer et al., RegNLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.regnlp-1.13.pdf