@inproceedings{chen-etal-2026-large-scale,
title = "Large-scale Multilingual News Image Captioning with {LLM}s",
author = "Chen, Yuji and
Velayuthan, Purushoth and
Plum, Alistair and
Hettiarachchi, Hansi and
Basnet, Saroj and
Velayuthan, Menan and
Zampieri, Marcos and
Ranasinghe, Tharindu",
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.1209/",
pages = "27652--27662",
ISBN = "979-8-89176-459-0",
abstract = "The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we \textbf{create the first large-scale multilingual news image captioning benchmark, LaMuN, comprising more than 800,000 news images in 59 languages, including several low-resource languages. We further propose a novel chain-of-thought method for automatic news image captioning that achieves state-of-the-art results across a diverse set of languages in LaMuN. Together, the benchmark and the proposed method open new avenues for further advances in developing and evaluating multilingual multimodal large language models.}"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-large-scale">
<titleInfo>
<title>Large-scale Multilingual News Image Captioning with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Purushoth</namePart>
<namePart type="family">Velayuthan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saroj</namePart>
<namePart type="family">Basnet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menan</namePart>
<namePart type="family">Velayuthan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</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>The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we create the first large-scale multilingual news image captioning benchmark, LaMuN, comprising more than 800,000 news images in 59 languages, including several low-resource languages. We further propose a novel chain-of-thought method for automatic news image captioning that achieves state-of-the-art results across a diverse set of languages in LaMuN. Together, the benchmark and the proposed method open new avenues for further advances in developing and evaluating multilingual multimodal large language models.</abstract>
<identifier type="citekey">chen-etal-2026-large-scale</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1209/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>27652</start>
<end>27662</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large-scale Multilingual News Image Captioning with LLMs
%A Chen, Yuji
%A Velayuthan, Purushoth
%A Plum, Alistair
%A Hettiarachchi, Hansi
%A Basnet, Saroj
%A Velayuthan, Menan
%A Zampieri, Marcos
%A Ranasinghe, Tharindu
%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 chen-etal-2026-large-scale
%X The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research on news image captioning focuses on English, primarily because datasets in other languages are scarce. To address this limitation, we create the first large-scale multilingual news image captioning benchmark, LaMuN, comprising more than 800,000 news images in 59 languages, including several low-resource languages. We further propose a novel chain-of-thought method for automatic news image captioning that achieves state-of-the-art results across a diverse set of languages in LaMuN. Together, the benchmark and the proposed method open new avenues for further advances in developing and evaluating multilingual multimodal large language models.
%U https://aclanthology.org/2026.emnlp-main.1209/
%P 27652-27662
Markdown (Informal)
[Large-scale Multilingual News Image Captioning with LLMs](https://aclanthology.org/2026.emnlp-main.1209/) (Chen et al., EMNLP 2026)
ACL
- Yuji Chen, Purushoth Velayuthan, Alistair Plum, Hansi Hettiarachchi, Saroj Basnet, Menan Velayuthan, Marcos Zampieri, and Tharindu Ranasinghe. 2026. Large-scale Multilingual News Image Captioning with LLMs. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 27652–27662, Budapest, Hungary. Association for Computational Linguistics.