@inproceedings{atuhurra-etal-2026-vlures,
title = "{VLUR}es: Benchmarking Long-Text Grounding and Cross-Lingual Robustness in Vision Language Models",
author = "Atuhurra, Jesse and
Ali, Iqra and
Iwakura, Tomoya and
Kamigaito, Hidetaka and
Hiraoka, Tatsuya",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings 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.findings-acl.1367/",
pages = "27426--27481",
ISBN = "979-8-89176-395-1",
abstract = "We introduce ***VLURes***, a multilingual benchmark for evaluating Vision-Language Models (VLMs) under *long-text grounding*: selecting and reasoning over the image-relevant subset of article-length text that contains distractors and ungrounded claims. *VLURes* contains **4,000** web-curated *image + long-text* pairs across **English (En), Japanese (Ja), Swahili (Sw), and Urdu (Ur)** and **10** topical categories, and defines **eight** tasks spanning image-only perception (OR, SU, RU, SS, IC) and image+text grounding (ITM, *Unrelatedness*, VQA). To construct web-realistic pairs, we apply language-adapted CLIP alignment to select representative images and filter weakly grounded pages. Across **10** proprietary and open VLMs evaluated under zero-shot and one-shot prompting, with and without rationales, the best model (GPT-4o) reaches **90.8{\%}** overall accuracy but remains **6.7** points below human performance (**97.5{\%}**) on Object Recognition, and cross-lingual sensitivity persists, while open models are substantially weaker and often lack reliable multilingual VL support. *VLURes* provides a practical testbed for long-text grounding and multilingual robustness in web-realistic agent settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atuhurra-etal-2026-vlures">
<titleInfo>
<title>VLURes: Benchmarking Long-Text Grounding and Cross-Lingual Robustness in Vision Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jesse</namePart>
<namePart type="family">Atuhurra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iqra</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoya</namePart>
<namePart type="family">Iwakura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Hiraoka</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>We introduce ***VLURes***, a multilingual benchmark for evaluating Vision-Language Models (VLMs) under *long-text grounding*: selecting and reasoning over the image-relevant subset of article-length text that contains distractors and ungrounded claims. *VLURes* contains **4,000** web-curated *image + long-text* pairs across **English (En), Japanese (Ja), Swahili (Sw), and Urdu (Ur)** and **10** topical categories, and defines **eight** tasks spanning image-only perception (OR, SU, RU, SS, IC) and image+text grounding (ITM, *Unrelatedness*, VQA). To construct web-realistic pairs, we apply language-adapted CLIP alignment to select representative images and filter weakly grounded pages. Across **10** proprietary and open VLMs evaluated under zero-shot and one-shot prompting, with and without rationales, the best model (GPT-4o) reaches **90.8%** overall accuracy but remains **6.7** points below human performance (**97.5%**) on Object Recognition, and cross-lingual sensitivity persists, while open models are substantially weaker and often lack reliable multilingual VL support. *VLURes* provides a practical testbed for long-text grounding and multilingual robustness in web-realistic agent settings.</abstract>
<identifier type="citekey">atuhurra-etal-2026-vlures</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1367/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>27426</start>
<end>27481</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VLURes: Benchmarking Long-Text Grounding and Cross-Lingual Robustness in Vision Language Models
%A Atuhurra, Jesse
%A Ali, Iqra
%A Iwakura, Tomoya
%A Kamigaito, Hidetaka
%A Hiraoka, Tatsuya
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F atuhurra-etal-2026-vlures
%X We introduce ***VLURes***, a multilingual benchmark for evaluating Vision-Language Models (VLMs) under *long-text grounding*: selecting and reasoning over the image-relevant subset of article-length text that contains distractors and ungrounded claims. *VLURes* contains **4,000** web-curated *image + long-text* pairs across **English (En), Japanese (Ja), Swahili (Sw), and Urdu (Ur)** and **10** topical categories, and defines **eight** tasks spanning image-only perception (OR, SU, RU, SS, IC) and image+text grounding (ITM, *Unrelatedness*, VQA). To construct web-realistic pairs, we apply language-adapted CLIP alignment to select representative images and filter weakly grounded pages. Across **10** proprietary and open VLMs evaluated under zero-shot and one-shot prompting, with and without rationales, the best model (GPT-4o) reaches **90.8%** overall accuracy but remains **6.7** points below human performance (**97.5%**) on Object Recognition, and cross-lingual sensitivity persists, while open models are substantially weaker and often lack reliable multilingual VL support. *VLURes* provides a practical testbed for long-text grounding and multilingual robustness in web-realistic agent settings.
%U https://aclanthology.org/2026.findings-acl.1367/
%P 27426-27481
Markdown (Informal)
[VLURes: Benchmarking Long-Text Grounding and Cross-Lingual Robustness in Vision Language Models](https://aclanthology.org/2026.findings-acl.1367/) (Atuhurra et al., Findings 2026)
ACL