@inproceedings{zan-etal-2026-exploring,
title = "Exploring Evidence-Grounded Review Generation with Multimodal Inline {RAG}",
author = "Zan, Mingrui and
Guo, Yuxin and
Zhang, Yunquan and
Ma, Shijie and
Zhang, Boyang and
Cheng, Daning and
Liu, Fangming",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.321/",
pages = "6789--6808",
ISBN = "979-8-89176-462-0",
abstract = "Multimodal review generation is essential in academic research. However, existing LLM-based models often struggle to pinpoint specific details within papers, yielding generalized, unsupported critiques that compromise final decisions. To address these limitations, we propose AnchorReviewer, a coarse-to-fine, evidence-grounded multimodal review generation framework. Central to our architecture is an integrated pipeline featuring an Inline Retrieval-Augmented Generation (InRAG) module. Combined with our Unified Embedding Module, InRAG facilitates the high-precision extraction of multimodal evidence chunks, ensuring our detailed reviews are strictly anchored to the original content. Furthermore, we incorporate a Reflection Mechanism to refine initial outputs and maximize decision accuracy. To support model evaluation and our Progressive Training Strategy, we construct the large-scale AnchorReview dataset, comprising diverse multimodal review samples. Experimental results demonstrate that AnchorReviewer significantly improves review reliability, excelling in critical evaluation, multimodal understanding, and decision consistency. Our code and dataset will be publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zan-etal-2026-exploring">
<titleInfo>
<title>Exploring Evidence-Grounded Review Generation with Multimodal Inline RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingrui</namePart>
<namePart type="family">Zan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunquan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijie</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daning</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Multimodal review generation is essential in academic research. However, existing LLM-based models often struggle to pinpoint specific details within papers, yielding generalized, unsupported critiques that compromise final decisions. To address these limitations, we propose AnchorReviewer, a coarse-to-fine, evidence-grounded multimodal review generation framework. Central to our architecture is an integrated pipeline featuring an Inline Retrieval-Augmented Generation (InRAG) module. Combined with our Unified Embedding Module, InRAG facilitates the high-precision extraction of multimodal evidence chunks, ensuring our detailed reviews are strictly anchored to the original content. Furthermore, we incorporate a Reflection Mechanism to refine initial outputs and maximize decision accuracy. To support model evaluation and our Progressive Training Strategy, we construct the large-scale AnchorReview dataset, comprising diverse multimodal review samples. Experimental results demonstrate that AnchorReviewer significantly improves review reliability, excelling in critical evaluation, multimodal understanding, and decision consistency. Our code and dataset will be publicly available.</abstract>
<identifier type="citekey">zan-etal-2026-exploring</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.321/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>6789</start>
<end>6808</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Evidence-Grounded Review Generation with Multimodal Inline RAG
%A Zan, Mingrui
%A Guo, Yuxin
%A Zhang, Yunquan
%A Ma, Shijie
%A Zhang, Boyang
%A Cheng, Daning
%A Liu, Fangming
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zan-etal-2026-exploring
%X Multimodal review generation is essential in academic research. However, existing LLM-based models often struggle to pinpoint specific details within papers, yielding generalized, unsupported critiques that compromise final decisions. To address these limitations, we propose AnchorReviewer, a coarse-to-fine, evidence-grounded multimodal review generation framework. Central to our architecture is an integrated pipeline featuring an Inline Retrieval-Augmented Generation (InRAG) module. Combined with our Unified Embedding Module, InRAG facilitates the high-precision extraction of multimodal evidence chunks, ensuring our detailed reviews are strictly anchored to the original content. Furthermore, we incorporate a Reflection Mechanism to refine initial outputs and maximize decision accuracy. To support model evaluation and our Progressive Training Strategy, we construct the large-scale AnchorReview dataset, comprising diverse multimodal review samples. Experimental results demonstrate that AnchorReviewer significantly improves review reliability, excelling in critical evaluation, multimodal understanding, and decision consistency. Our code and dataset will be publicly available.
%U https://aclanthology.org/2026.findings-emnlp.321/
%P 6789-6808
Markdown (Informal)
[Exploring Evidence-Grounded Review Generation with Multimodal Inline RAG](https://aclanthology.org/2026.findings-emnlp.321/) (Zan et al., Findings 2026)
ACL