@inproceedings{wang-etal-2026-flow,
title = "Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering",
author = "Wang, Haosen and
Xiao, Jing and
Du, Chaochao and
Zhang, Xiaowang and
Feng, Zhiyong",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1679/",
pages = "36260--36280",
ISBN = "979-8-89176-390-6",
abstract = "Document Visual Question Answering (DocVQA) aims to generate answers by jointly understanding the textual, layout, and visual elements within document images. Although end-to-end vision-based generative methods have reduced dependency on OCR, they still struggle to achieve precise evidence localization when page semantics are complex and highly similar. However, existing research lacks an in-depth theoretical analysis of the question-driven semantic representation space, failing to fundamentally address the distinguishability problem among semantically similar pages. To fill this theoretical gap, we propose and prove that, given a specific question, each page possesses a unique semantic representation, and there exists a bijective mapping between the page and its unique semantics. Based on this theoretical foundation, we introduce the \textbf{F}low-Based Page \textbf{U}nique Semantic \textbf{M}apping \textbf{A}rchitecture (\textbf{FUMA}), which reconstructs evidence localization from similarity-based retrieval into precise selection on unique semantics. FUMA employs fine-grained cross-modal attention to extract discriminative cues and utilizes flow-based reversible transformations with likelihood regularization to learn bijective mappings, ensuring that each page obtains a unique semantic representation. Moreover, a multi-expert collaboration mechanism complementarily models fine-grained multimodal information within each page, achieving robust answer generation. Experimental results demonstrate that FUMA significantly outperforms existing methods in both evidence localization and answer generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-flow">
<titleInfo>
<title>Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haosen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaochao</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaowang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Feng</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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Document Visual Question Answering (DocVQA) aims to generate answers by jointly understanding the textual, layout, and visual elements within document images. Although end-to-end vision-based generative methods have reduced dependency on OCR, they still struggle to achieve precise evidence localization when page semantics are complex and highly similar. However, existing research lacks an in-depth theoretical analysis of the question-driven semantic representation space, failing to fundamentally address the distinguishability problem among semantically similar pages. To fill this theoretical gap, we propose and prove that, given a specific question, each page possesses a unique semantic representation, and there exists a bijective mapping between the page and its unique semantics. Based on this theoretical foundation, we introduce the Flow-Based Page Unique Semantic Mapping Architecture (FUMA), which reconstructs evidence localization from similarity-based retrieval into precise selection on unique semantics. FUMA employs fine-grained cross-modal attention to extract discriminative cues and utilizes flow-based reversible transformations with likelihood regularization to learn bijective mappings, ensuring that each page obtains a unique semantic representation. Moreover, a multi-expert collaboration mechanism complementarily models fine-grained multimodal information within each page, achieving robust answer generation. Experimental results demonstrate that FUMA significantly outperforms existing methods in both evidence localization and answer generation.</abstract>
<identifier type="citekey">wang-etal-2026-flow</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1679/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>36260</start>
<end>36280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering
%A Wang, Haosen
%A Xiao, Jing
%A Du, Chaochao
%A Zhang, Xiaowang
%A Feng, Zhiyong
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wang-etal-2026-flow
%X Document Visual Question Answering (DocVQA) aims to generate answers by jointly understanding the textual, layout, and visual elements within document images. Although end-to-end vision-based generative methods have reduced dependency on OCR, they still struggle to achieve precise evidence localization when page semantics are complex and highly similar. However, existing research lacks an in-depth theoretical analysis of the question-driven semantic representation space, failing to fundamentally address the distinguishability problem among semantically similar pages. To fill this theoretical gap, we propose and prove that, given a specific question, each page possesses a unique semantic representation, and there exists a bijective mapping between the page and its unique semantics. Based on this theoretical foundation, we introduce the Flow-Based Page Unique Semantic Mapping Architecture (FUMA), which reconstructs evidence localization from similarity-based retrieval into precise selection on unique semantics. FUMA employs fine-grained cross-modal attention to extract discriminative cues and utilizes flow-based reversible transformations with likelihood regularization to learn bijective mappings, ensuring that each page obtains a unique semantic representation. Moreover, a multi-expert collaboration mechanism complementarily models fine-grained multimodal information within each page, achieving robust answer generation. Experimental results demonstrate that FUMA significantly outperforms existing methods in both evidence localization and answer generation.
%U https://aclanthology.org/2026.acl-long.1679/
%P 36260-36280
Markdown (Informal)
[Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering](https://aclanthology.org/2026.acl-long.1679/) (Wang et al., ACL 2026)
ACL