@inproceedings{liu-etal-2025-bridging-underspecified,
    title = "Bridging Underspecified Queries and Multimodal Retrieval: A Two-Stage Query Rewriting Approach",
    author = "Liu, Szu-Ting  and
      Cho, Wen-Yu  and
      Wang, Hsin-Wei  and
      Chen, Berlin",
    editor = "Chang, Kai-Wei  and
      Lu, Ke-Han  and
      Yang, Chih-Kai  and
      Tam, Zhi-Rui  and
      Chang, Wen-Yu  and
      Wang, Chung-Che",
    booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
    month = nov,
    year = "2025",
    address = "National Taiwan University, Taipei City, Taiwan",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/dashboard/2025.rocling-main.7/",
    pages = "63--70",
    ISBN = "979-8-89176-379-1",
    abstract = "Retrieval-Augmented Generation (RAG) has proven effective for text-only question answering, yet expanding it to visually rich documents remains a challenge. Existing multimodal benchmarks, often derived from visual question answering (VQA) datasets, or large vision-language model (LVLM)-generated query-image pairs, which often contain underspecified questions that assume direct image access. To mitigate this issue, we propose a two-stage query rewriting framework that first generates OCR-based image descriptions and then reformulates queries into precise, retrieval-friendly forms under explicit constraints. Experiments show consistent improvements across dense, hybrid and multimodal retrieval paradigms, with the most pronounced gains in visual document retrieval {--} Hits@1 rises from 21.0{\%} to 56.6{\%} with VDocRetriever and further to 79.3{\%} when OCR-based descriptions are incorporated. These results indicate that query rewriting, particularly when combined with multimodal fusion, provides a reliable and scalable solution to bridge underspecified queries and improve retrieval over visually rich documents."
}