@inproceedings{wu-etal-2025-doc,
    title = "Doc-React: Multi-page Heterogeneous Document Question-answering",
    author = "Wu, Junda  and
      Xia, Yu  and
      Yu, Tong  and
      Chen, Xiang  and
      Harsha, Sai Sree  and
      Maharaj, Akash V  and
      Zhang, Ruiyi  and
      Bursztyn, Victor  and
      Kim, Sungchul  and
      Rossi, Ryan A.  and
      McAuley, Julian  and
      Li, Yunyao  and
      Sinha, Ritwik",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-short.6/",
    pages = "67--78",
    ISBN = "979-8-89176-252-7",
    abstract = "Answering questions over multi-page, multimodal documents, including text and figures, is a critical challenge for applications that require answers to integrate information across multiple modalities and contextual dependencies. Existing methods, such as single-turn retrieval-augmented generation (RAG), struggle to retrieve fine-grained and contextually relevant information from large, heterogeneous documents, leading to suboptimal performance. Inspired by iterative frameworks like ReAct, which refine retrieval through feedback, we propose Doc-React, an adaptive iterative framework that balances information gain and uncertainty reduction at each step. Doc-React leverages InfoNCE-guided retrieval to approximate mutual information, enabling dynamic sub-query generation and refinement. A large language model (LLM) serves as both a judge and generator, providing structured feedback to iteratively improve retrieval. By combining mutual information optimization with entropy-aware selection, Doc-React systematically captures relevant multimodal content, achieving strong performance on complex QA tasks"
}