@inproceedings{dash-etal-2026-towards,
title = "Towards Improving Multimodal Machine Translation with {LLM}s: A Focus on {I}ndic Languages",
author = "Dash, Amulya Ratna and
Wadhwa, Chirag and
Sharma, Yashvardhan",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.698/",
doi = "10.63317/4od6be42j78m",
pages = "8872--8882",
abstract = "Recent advances in Multimodal Machine Translation (MMT) have attempted to address ambiguity and polysemy in text alone by enabling models to draw additional contextual cues from paired images, thereby improving disambiguation and translation accuracy. Datasets such as Multi30K and Visual Genome have significantly advanced this line of research. However, these datasets do not always compel models to rely on visual information. The CoMMuTE dataset takes a stronger step in this direction by serving as an evaluation benchmark specifically designed around ambiguous English sentences that can only be correctly interpreted with their accompanying images. In this work, we extend CoMMuTE to two Indic languages, introducing IndicCoMMuTE {---} an evaluation dataset for assessing MMT systems on low-resource Indic languages. We benchmark a range of open-source multimodal Large Language Models ({\ensuremath{<}} 15B parameters) and a strong text-only baseline across eight languages. We fine-tune one of these LLMs on two Indic languages. Our findings provide insights into the strengths and limitations of LLMs and establish IndicCoMMuTE as a valuable benchmark for future research on Multimodal Machine Translation in Indic languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dash-etal-2026-towards">
<titleInfo>
<title>Towards Improving Multimodal Machine Translation with LLMs: A Focus on Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amulya</namePart>
<namePart type="given">Ratna</namePart>
<namePart type="family">Dash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chirag</namePart>
<namePart type="family">Wadhwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yashvardhan</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in Multimodal Machine Translation (MMT) have attempted to address ambiguity and polysemy in text alone by enabling models to draw additional contextual cues from paired images, thereby improving disambiguation and translation accuracy. Datasets such as Multi30K and Visual Genome have significantly advanced this line of research. However, these datasets do not always compel models to rely on visual information. The CoMMuTE dataset takes a stronger step in this direction by serving as an evaluation benchmark specifically designed around ambiguous English sentences that can only be correctly interpreted with their accompanying images. In this work, we extend CoMMuTE to two Indic languages, introducing IndicCoMMuTE — an evaluation dataset for assessing MMT systems on low-resource Indic languages. We benchmark a range of open-source multimodal Large Language Models (\ensuremath< 15B parameters) and a strong text-only baseline across eight languages. We fine-tune one of these LLMs on two Indic languages. Our findings provide insights into the strengths and limitations of LLMs and establish IndicCoMMuTE as a valuable benchmark for future research on Multimodal Machine Translation in Indic languages.</abstract>
<identifier type="citekey">dash-etal-2026-towards</identifier>
<identifier type="doi">10.63317/4od6be42j78m</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.698/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8872</start>
<end>8882</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Improving Multimodal Machine Translation with LLMs: A Focus on Indic Languages
%A Dash, Amulya Ratna
%A Wadhwa, Chirag
%A Sharma, Yashvardhan
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F dash-etal-2026-towards
%X Recent advances in Multimodal Machine Translation (MMT) have attempted to address ambiguity and polysemy in text alone by enabling models to draw additional contextual cues from paired images, thereby improving disambiguation and translation accuracy. Datasets such as Multi30K and Visual Genome have significantly advanced this line of research. However, these datasets do not always compel models to rely on visual information. The CoMMuTE dataset takes a stronger step in this direction by serving as an evaluation benchmark specifically designed around ambiguous English sentences that can only be correctly interpreted with their accompanying images. In this work, we extend CoMMuTE to two Indic languages, introducing IndicCoMMuTE — an evaluation dataset for assessing MMT systems on low-resource Indic languages. We benchmark a range of open-source multimodal Large Language Models (\ensuremath< 15B parameters) and a strong text-only baseline across eight languages. We fine-tune one of these LLMs on two Indic languages. Our findings provide insights into the strengths and limitations of LLMs and establish IndicCoMMuTE as a valuable benchmark for future research on Multimodal Machine Translation in Indic languages.
%R 10.63317/4od6be42j78m
%U https://aclanthology.org/2026.lrec-1.698/
%U https://doi.org/10.63317/4od6be42j78m
%P 8872-8882
Markdown (Informal)
[Towards Improving Multimodal Machine Translation with LLMs: A Focus on Indic Languages](https://aclanthology.org/2026.lrec-1.698/) (Dash et al., LREC 2026)
ACL