@inproceedings{kajita-etal-2026-presentation,
title = "Presentation Slide Translation and Layout Error Correction by {LLM}s",
author = "Kajita, Futo and
Nishimura, Nobuyori and
Utsuro, Takehito and
Muto, Naoki and
Leow, Chee Siang and
Nishizaki, Hiromitsu",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.26/",
pages = "326--339",
ISBN = "979-8-89176-393-7",
abstract = "We propose a novel approach to translating Japanese slides into English andto correcting their layout errors by utilizing multimodal LLMs with slide images and XML structures.Existing translation tools often suffer from layout errors after translationdue to text expansion during the translation process, causing text to overlap with figures or other items in slides and thereby reducing readability. To overcome this issue, our proposed framework introduces two steps consisting of (i) translating text fragments within the slide, and (ii) correcting layout errors by optimizing layout placement based on visual consistency. In step (ii), we empirically show that few-shot prompts are quite effective in layout error correction. Given that the optimal combination of steps (i) and (ii) varies depending on the slide layout, our method generates eight different layout candidates. Consequently, we introduce a third step that automatically selects the optimal output from these eight candidates.The experimental results showed that the proposed method outperformed baselines and achieved 4.1{\%} layout error rate and over 80{\%} model selection success rate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kajita-etal-2026-presentation">
<titleInfo>
<title>Presentation Slide Translation and Layout Error Correction by LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Futo</namePart>
<namePart type="family">Kajita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nobuyori</namePart>
<namePart type="family">Nishimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Muto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chee</namePart>
<namePart type="given">Siang</namePart>
<namePart type="family">Leow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiromitsu</namePart>
<namePart type="family">Nishizaki</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 (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</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">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>We propose a novel approach to translating Japanese slides into English andto correcting their layout errors by utilizing multimodal LLMs with slide images and XML structures.Existing translation tools often suffer from layout errors after translationdue to text expansion during the translation process, causing text to overlap with figures or other items in slides and thereby reducing readability. To overcome this issue, our proposed framework introduces two steps consisting of (i) translating text fragments within the slide, and (ii) correcting layout errors by optimizing layout placement based on visual consistency. In step (ii), we empirically show that few-shot prompts are quite effective in layout error correction. Given that the optimal combination of steps (i) and (ii) varies depending on the slide layout, our method generates eight different layout candidates. Consequently, we introduce a third step that automatically selects the optimal output from these eight candidates.The experimental results showed that the proposed method outperformed baselines and achieved 4.1% layout error rate and over 80% model selection success rate.</abstract>
<identifier type="citekey">kajita-etal-2026-presentation</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.26/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>326</start>
<end>339</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Presentation Slide Translation and Layout Error Correction by LLMs
%A Kajita, Futo
%A Nishimura, Nobuyori
%A Utsuro, Takehito
%A Muto, Naoki
%A Leow, Chee Siang
%A Nishizaki, Hiromitsu
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F kajita-etal-2026-presentation
%X We propose a novel approach to translating Japanese slides into English andto correcting their layout errors by utilizing multimodal LLMs with slide images and XML structures.Existing translation tools often suffer from layout errors after translationdue to text expansion during the translation process, causing text to overlap with figures or other items in slides and thereby reducing readability. To overcome this issue, our proposed framework introduces two steps consisting of (i) translating text fragments within the slide, and (ii) correcting layout errors by optimizing layout placement based on visual consistency. In step (ii), we empirically show that few-shot prompts are quite effective in layout error correction. Given that the optimal combination of steps (i) and (ii) varies depending on the slide layout, our method generates eight different layout candidates. Consequently, we introduce a third step that automatically selects the optimal output from these eight candidates.The experimental results showed that the proposed method outperformed baselines and achieved 4.1% layout error rate and over 80% model selection success rate.
%U https://aclanthology.org/2026.acl-srw.26/
%P 326-339
Markdown (Informal)
[Presentation Slide Translation and Layout Error Correction by LLMs](https://aclanthology.org/2026.acl-srw.26/) (Kajita et al., ACL 2026)
ACL
- Futo Kajita, Nobuyori Nishimura, Takehito Utsuro, Naoki Muto, Chee Siang Leow, and Hiromitsu Nishizaki. 2026. Presentation Slide Translation and Layout Error Correction by LLMs. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 326–339, San Diego, California, United States. Association for Computational Linguistics.