@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakraborty-etal-2026-marquis">
<titleInfo>
<title>MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debashish</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dengjia</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialiang</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Guerrerio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanxiang</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Skow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reno</namePart>
<namePart type="family">Kriz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Van Durme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reno</namePart>
<namePart type="family">Kriz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-425-5</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">chakraborty-etal-2026-marquis</identifier>
<location>
<url>https://aclanthology.org/2026.magmar-main.13/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>92</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation
%A Chakraborty, Debashish
%A Zhang, Dengjia
%A Jin, Jialiang
%A Guerrerio, Katherine M.
%A Liu, Hanting
%A Qin, Hanxiang
%A Skow, Tyler
%A Martin, Alexander
%A Kriz, Reno
%A Van Durme, Benjamin
%Y Murray, Kenton
%Y Kriz, Reno
%S Proceedings of the 2nd Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA
%@ 979-8-89176-425-5
%F chakraborty-etal-2026-marquis
%X 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.
%U https://aclanthology.org/2026.magmar-main.13/
%P 92-119
Markdown (Informal)
[MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation](https://aclanthology.org/2026.magmar-main.13/) (Chakraborty et al., MAGMaR 2026)
ACL
- Debashish Chakraborty, Dengjia Zhang, Jialiang Jin, Katherine M. Guerrerio, Hanting Liu, Hanxiang Qin, Tyler Skow, Alexander Martin, Reno Kriz, and Benjamin Van Durme. 2026. MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation. In Proceedings of the 2nd Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2026), pages 92–119, San Diego, USA. Association for Computational Linguistics.