@inproceedings{shan-etal-2026-factverse,
title = "{F}act{V}erse: A Benchmark for Factual Consistency in Interleaved Image{--}Text Generation",
author = "Shan, Yubo and
Zhang, Kun and
Xu, Qiming and
Cao, Liping and
Cao, Yingying and
Zhang, Jian and
Wang, Yu and
Li, Jingyuan and
Wang, Yuanzhuo",
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.1323/",
pages = "28666--28689",
ISBN = "979-8-89176-390-6",
abstract = "Interleaved multimodal understanding and generation{---}where models can interactively comprehend and produce images and text in arbitrary orders{---}has emerged as a key research direction in generative Multimodal Large Language Models(MLLMs). Such interleaved image{--}text content plays an increasingly important role in information dissemination. However, the compounded persuasive power of multimodal narratives also raises the risk of factual misinformation. Despite this, existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image{--}text content. To bridge this gap, we introduce FactVerse, a benchmark dedicated to evaluating factual consistency in interleaved image-text generation. FactVerse comprises 3,000 human-verified instances across four categories and 50 domains, supporting both English and Chinese. We also establish a multi-dimensional evaluation framework designed to rigorously assess factual consistency. Experiments demonstrate that our framework achieves high alignment with human judgments, significantly outperforming existing evaluation methods. Furthermore, our analysis reveals systematic deficiencies in current models, offering critical insights for future design."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shan-etal-2026-factverse">
<titleInfo>
<title>FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Shan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiming</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liping</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingying</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanzhuo</namePart>
<namePart type="family">Wang</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>Interleaved multimodal understanding and generation—where models can interactively comprehend and produce images and text in arbitrary orders—has emerged as a key research direction in generative Multimodal Large Language Models(MLLMs). Such interleaved image–text content plays an increasingly important role in information dissemination. However, the compounded persuasive power of multimodal narratives also raises the risk of factual misinformation. Despite this, existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image–text content. To bridge this gap, we introduce FactVerse, a benchmark dedicated to evaluating factual consistency in interleaved image-text generation. FactVerse comprises 3,000 human-verified instances across four categories and 50 domains, supporting both English and Chinese. We also establish a multi-dimensional evaluation framework designed to rigorously assess factual consistency. Experiments demonstrate that our framework achieves high alignment with human judgments, significantly outperforming existing evaluation methods. Furthermore, our analysis reveals systematic deficiencies in current models, offering critical insights for future design.</abstract>
<identifier type="citekey">shan-etal-2026-factverse</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1323/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>28666</start>
<end>28689</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation
%A Shan, Yubo
%A Zhang, Kun
%A Xu, Qiming
%A Cao, Liping
%A Cao, Yingying
%A Zhang, Jian
%A Wang, Yu
%A Li, Jingyuan
%A Wang, Yuanzhuo
%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 shan-etal-2026-factverse
%X Interleaved multimodal understanding and generation—where models can interactively comprehend and produce images and text in arbitrary orders—has emerged as a key research direction in generative Multimodal Large Language Models(MLLMs). Such interleaved image–text content plays an increasingly important role in information dissemination. However, the compounded persuasive power of multimodal narratives also raises the risk of factual misinformation. Despite this, existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image–text content. To bridge this gap, we introduce FactVerse, a benchmark dedicated to evaluating factual consistency in interleaved image-text generation. FactVerse comprises 3,000 human-verified instances across four categories and 50 domains, supporting both English and Chinese. We also establish a multi-dimensional evaluation framework designed to rigorously assess factual consistency. Experiments demonstrate that our framework achieves high alignment with human judgments, significantly outperforming existing evaluation methods. Furthermore, our analysis reveals systematic deficiencies in current models, offering critical insights for future design.
%U https://aclanthology.org/2026.acl-long.1323/
%P 28666-28689
Markdown (Informal)
[FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation](https://aclanthology.org/2026.acl-long.1323/) (Shan et al., ACL 2026)
ACL
- Yubo Shan, Kun Zhang, Qiming Xu, Liping Cao, Yingying Cao, Jian Zhang, Yu Wang, Jingyuan Li, and Yuanzhuo Wang. 2026. FactVerse: A Benchmark for Factual Consistency in Interleaved Image–Text Generation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 28666–28689, San Diego, California, United States. Association for Computational Linguistics.