@inproceedings{khan-etal-2025-nust,
    title = "{NUST} Nova at {RIRAG} 2025: A Hybrid Framework for Regulatory Information Retrieval and Question Answering",
    author = "Khan, Mariam Babar  and
      Ameer, Huma  and
      Latif, Seemab  and
      Fatima, Mehwish",
    editor = "Gokhan, Tuba  and
      Wang, Kexin  and
      Gurevych, Iryna  and
      Briscoe, Ted",
    booktitle = "Proceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.regnlp-1.11/",
    pages = "73--78",
    abstract = "NUST Nova participates in RIRAG Shared Task, addressing two critical challenges: Task 1 involves retrieving relevant subsections from regulatory documents based on user queries, while Task 2 focuses on generating concise, contextually accurate answers using the retrieved information. We propose a Hybrid Retrieval Framework that combines graph-based retrieval, vector-based methods, and keyword matching BM25 to enhance relevance and precision in regulatory QA. Using score-based fusion and iterative refinement, the framework retrieves the top 10 relevant passages, which are then used by an LLM to generate accurate, context-aware answers. After empirical evaluation, we also conduct an error analysis to identify our framework{'}s limitations."
}