@inproceedings{in-etal-2025-diversify,
    title = "Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering",
    author = "In, Yeonjun  and
      Kim, Sungchul  and
      Rossi, Ryan A.  and
      Tanjim, Mehrab  and
      Yu, Tong  and
      Sinha, Ritwik  and
      Park, Chanyoung",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.naacl-long.56/",
    pages = "1212--1233",
    ISBN = "979-8-89176-189-6",
    abstract = "The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However, our preliminary studies reveal that a single retrieval process often suffers from low-quality results, as the retrieved passages frequently fail to capture all plausible interpretations. Although the iterative RAG approach has been proposed to address this problem, it comes at the cost of significantly reduced efficiency. To address these issues, we propose the diversify-verify-adapt (DIVA) framework. DIVA first diversifies the retrieved passages to encompass diverse interpretations. Subsequently, DIVA verifies the quality of the passages and adapts the most suitable approach tailored to their quality. This approach improves the QA systems' accuracy and robustness by handling low quality retrieval issue in ambiguous questions, while enhancing efficiency."
}