@inproceedings{wang-etal-2025-beyond-single,
title = "Beyond Single Frames: Can {LMM}s Comprehend Implicit Narratives in Comic Strip?",
author = "Wang, Xiaochen and
Xia, Heming and
Song, Jialin and
Guan, Longyu and
Dong, Qingxiu and
Li, Rui and
Yang, Yixin and
Pu, Yifan and
Luo, Weiyao and
Wang, Yiru and
Meng, Xiangdi and
Li, Wenjie and
Sui, Zhifang",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.342/",
pages = "6436--6452",
ISBN = "979-8-89176-335-7",
abstract = "Large Multimodal Models (LMMs) have demonstrated strong performance on vision-language benchmarks, yet current evaluations predominantly focus on single-image reasoning. In contrast, real-world scenarios always involve understanding sequences of images. A typical scenario is comic strips understanding, which requires models to perform nuanced visual reasoning beyond surface-level recognition. To address this gap, we introduce STRIPCIPHER , a benchmark designed to evaluate the model ability on understanding implicit narratives in silent comics. STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels. It comprises three tasks: visual narrative comprehension, contextual frame prediction, and temporal narrative reordering. {\%} , covering various difficulty. Notably, evaluation results on STRIPCIPHER reveals a significant gap between current LMMs and human performance{---}e.g., GPT-4o achieves only 23.93{\%} accuracy in the reordering task, 56.07{\%} below human levels. These findings underscore the limitations of current LMMs in implicit visual narrative understanding and highlight opportunities for advancing sequential multimodal reasoning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-beyond-single">
<titleInfo>
<title>Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaochen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heming</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialin</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longyu</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingxiu</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Pu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyao</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiru</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangdi</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhifang</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Large Multimodal Models (LMMs) have demonstrated strong performance on vision-language benchmarks, yet current evaluations predominantly focus on single-image reasoning. In contrast, real-world scenarios always involve understanding sequences of images. A typical scenario is comic strips understanding, which requires models to perform nuanced visual reasoning beyond surface-level recognition. To address this gap, we introduce STRIPCIPHER , a benchmark designed to evaluate the model ability on understanding implicit narratives in silent comics. STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels. It comprises three tasks: visual narrative comprehension, contextual frame prediction, and temporal narrative reordering. % , covering various difficulty. Notably, evaluation results on STRIPCIPHER reveals a significant gap between current LMMs and human performance—e.g., GPT-4o achieves only 23.93% accuracy in the reordering task, 56.07% below human levels. These findings underscore the limitations of current LMMs in implicit visual narrative understanding and highlight opportunities for advancing sequential multimodal reasoning.</abstract>
<identifier type="citekey">wang-etal-2025-beyond-single</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.342/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>6436</start>
<end>6452</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip?
%A Wang, Xiaochen
%A Xia, Heming
%A Song, Jialin
%A Guan, Longyu
%A Dong, Qingxiu
%A Li, Rui
%A Yang, Yixin
%A Pu, Yifan
%A Luo, Weiyao
%A Wang, Yiru
%A Meng, Xiangdi
%A Li, Wenjie
%A Sui, Zhifang
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F wang-etal-2025-beyond-single
%X Large Multimodal Models (LMMs) have demonstrated strong performance on vision-language benchmarks, yet current evaluations predominantly focus on single-image reasoning. In contrast, real-world scenarios always involve understanding sequences of images. A typical scenario is comic strips understanding, which requires models to perform nuanced visual reasoning beyond surface-level recognition. To address this gap, we introduce STRIPCIPHER , a benchmark designed to evaluate the model ability on understanding implicit narratives in silent comics. STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels. It comprises three tasks: visual narrative comprehension, contextual frame prediction, and temporal narrative reordering. % , covering various difficulty. Notably, evaluation results on STRIPCIPHER reveals a significant gap between current LMMs and human performance—e.g., GPT-4o achieves only 23.93% accuracy in the reordering task, 56.07% below human levels. These findings underscore the limitations of current LMMs in implicit visual narrative understanding and highlight opportunities for advancing sequential multimodal reasoning.
%U https://aclanthology.org/2025.findings-emnlp.342/
%P 6436-6452
Markdown (Informal)
[Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip?](https://aclanthology.org/2025.findings-emnlp.342/) (Wang et al., Findings 2025)
ACL
- Xiaochen Wang, Heming Xia, Jialin Song, Longyu Guan, Qingxiu Dong, Rui Li, Yixin Yang, Yifan Pu, Weiyao Luo, Yiru Wang, Xiangdi Meng, Wenjie Li, and Zhifang Sui. 2025. Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip?. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 6436–6452, Suzhou, China. Association for Computational Linguistics.