@inproceedings{chakraborty-etal-2026-marquis,
    title = "{MARQUIS}: A Three-Stage Pipeline for Video Retrieval-Augmented Generation",
    author = "Chakraborty, Debashish  and
      Zhang, Dengjia  and
      Jin, Jialiang  and
      Guerrerio, Katherine M.  and
      Liu, Hanting  and
      Qin, Hanxiang  and
      Skow, Tyler  and
      Martin, Alexander  and
      Kriz, Reno  and
      Van Durme, Benjamin",
    editor = "Murray, Kenton  and
      Kriz, Reno",
    booktitle = "Proceedings of the 2nd Workshop on Multimodal Augmented Generation via Multimodal Retrieval ({MAGM}a{R} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.magmar-main.13/",
    pages = "92--119",
    ISBN = "979-8-89176-425-5",
    abstract = "Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into coherent, attributed text. Current approaches struggle at both ends: retrieval methods fail on complex, multi-faceted queries that cannot be captured by a single embedding, while generation methods lack the high-level reasoning needed to synthesize across multiple videos and face memory constraints over long, multi-video contexts. We present MARQUIS: a three-stage pipeline that addresses these limitations through (1) query expansion, fusion, and reranking, (2) calibrated structured evidence extraction, and (3) article generation from extracted evidence, optionally controlled by an RLM. On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems."
}