@inproceedings{dong-etal-2026-insight,
title = "{INSIGHT}: Structured Multimodal Knowledge Modeling for Vision-Guided Task-Oriented Dialogue",
author = "Dong, Xuelian and
Chen, Jiale and
Hao, Tianyong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.881/",
pages = "20344--20360",
ISBN = "979-8-89176-459-0",
abstract = "In real-world task-oriented dialogue (TOD), users often express their intents through both text and images, with images providing essential cues for fine-grained requirements. Addressing such scenarios demands effective cross-modal semantic modeling and precise knowledge retrieval. However, existing TOD methods primarily focus on text and assume one-to-one attribute mappings, failing to reflect the multimodal nature of real-world information. To overcome these limitations, this paper proposes an end-to-end vision-guided retrieval-generation framework named INSIGHT. It introduces a progressive dynamic fusion mechanism that performs layer-wise cross-modal interaction to achieve robust multimodal dialogue understanding. In addition, a graph-structured entity modeling strategy explicitly models one-to-many image attribute mappings through distributed latent semantic learning, thereby preserving visual diversity. Finally, knowledge retrieval and response generation are jointly optimized in an end-to-end manner. To evaluate real-world scenarios, we construct VISTA, a new multimodal TOD dataset that features image-driven multi-turn dialogues and supports one-to-many entity attribute mappings. Experimental results on two multimodal datasets demonstrate that INSIGHT consistently outperforms existing methods across various backbone models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2026-insight">
<titleInfo>
<title>INSIGHT: Structured Multimodal Knowledge Modeling for Vision-Guided Task-Oriented Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuelian</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiale</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyong</namePart>
<namePart type="family">Hao</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>In real-world task-oriented dialogue (TOD), users often express their intents through both text and images, with images providing essential cues for fine-grained requirements. Addressing such scenarios demands effective cross-modal semantic modeling and precise knowledge retrieval. However, existing TOD methods primarily focus on text and assume one-to-one attribute mappings, failing to reflect the multimodal nature of real-world information. To overcome these limitations, this paper proposes an end-to-end vision-guided retrieval-generation framework named INSIGHT. It introduces a progressive dynamic fusion mechanism that performs layer-wise cross-modal interaction to achieve robust multimodal dialogue understanding. In addition, a graph-structured entity modeling strategy explicitly models one-to-many image attribute mappings through distributed latent semantic learning, thereby preserving visual diversity. Finally, knowledge retrieval and response generation are jointly optimized in an end-to-end manner. To evaluate real-world scenarios, we construct VISTA, a new multimodal TOD dataset that features image-driven multi-turn dialogues and supports one-to-many entity attribute mappings. Experimental results on two multimodal datasets demonstrate that INSIGHT consistently outperforms existing methods across various backbone models.</abstract>
<identifier type="citekey">dong-etal-2026-insight</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.881/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>20344</start>
<end>20360</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T INSIGHT: Structured Multimodal Knowledge Modeling for Vision-Guided Task-Oriented Dialogue
%A Dong, Xuelian
%A Chen, Jiale
%A Hao, Tianyong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F dong-etal-2026-insight
%X In real-world task-oriented dialogue (TOD), users often express their intents through both text and images, with images providing essential cues for fine-grained requirements. Addressing such scenarios demands effective cross-modal semantic modeling and precise knowledge retrieval. However, existing TOD methods primarily focus on text and assume one-to-one attribute mappings, failing to reflect the multimodal nature of real-world information. To overcome these limitations, this paper proposes an end-to-end vision-guided retrieval-generation framework named INSIGHT. It introduces a progressive dynamic fusion mechanism that performs layer-wise cross-modal interaction to achieve robust multimodal dialogue understanding. In addition, a graph-structured entity modeling strategy explicitly models one-to-many image attribute mappings through distributed latent semantic learning, thereby preserving visual diversity. Finally, knowledge retrieval and response generation are jointly optimized in an end-to-end manner. To evaluate real-world scenarios, we construct VISTA, a new multimodal TOD dataset that features image-driven multi-turn dialogues and supports one-to-many entity attribute mappings. Experimental results on two multimodal datasets demonstrate that INSIGHT consistently outperforms existing methods across various backbone models.
%U https://aclanthology.org/2026.emnlp-main.881/
%P 20344-20360
Markdown (Informal)
[INSIGHT: Structured Multimodal Knowledge Modeling for Vision-Guided Task-Oriented Dialogue](https://aclanthology.org/2026.emnlp-main.881/) (Dong et al., EMNLP 2026)
ACL