@inproceedings{vo-2026-team,
title = "Team {H}alluci{N}auts at {SHROOM}-Visions: Anchor-Preserving Dual-Resolution Grounding for Fine-Grained Vision Hallucination Detection",
author = "Vo, Khang Nhat Hoang",
editor = {Aziz, Wilker and
Berant, Jonathan and
Eikema, Bryan and
Ilia, Evgenia and
de Marneffe, Marie-Catherine and
Plank, Barbara and
Shelmanov, Artem and
Swayamdipta, Swabha and
Tiedemann, J{\"o}rg and
Vazhentsev, Artem and
V{\'a}zquez, Ra{\'u}l and
Zerva, Chrysoula},
booktitle = "The Proceedings of the Third Workshop on Uncertainty-Aware {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.uncertainlp-main.44/",
pages = "715--721",
ISBN = "979-8-89176-486-6",
abstract = "We describe our submission to the SHROOM-Visions 2026 English task, which requires detecting hallucinated character spans in image-conditioned responses, assigning confidence scores, and classifying each span as invention, mischaracterization, OCR error, miscounting, or other. Our system combines ModernBERT-large with frozen SigLIP2 patch features at $224\times224$ and $384\times384$ resolutions. A primary cross-modal detector produces token-level predictions, while a high-resolution branch adds bounded grounding and anchor-preserving residual corrections. The system uses only the official English training data and publicly available pretrained backbones, without retrieval, generated captions, external OCR, or additional labeled data. Post-hoc ablations show that the anchor-preserving correction provides the clearest incremental gain, while mismatched-image supervision has negligible development impact and histogram calibration is not beneficial. The submitted system achieves 0.2942 \textsc{Cor} and 0.2140 \textsc{Cor+Lbl} on the public leaderboard."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vo-2026-team">
<titleInfo>
<title>Team HalluciNauts at SHROOM-Visions: Anchor-Preserving Dual-Resolution Grounding for Fine-Grained Vision Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Khang</namePart>
<namePart type="given">Nhat</namePart>
<namePart type="given">Hoang</namePart>
<namePart type="family">Vo</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>The Proceedings of the Third Workshop on Uncertainty-Aware NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Eikema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Ilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Vazhentsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</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">979-8-89176-486-6</identifier>
</relatedItem>
<abstract>We describe our submission to the SHROOM-Visions 2026 English task, which requires detecting hallucinated character spans in image-conditioned responses, assigning confidence scores, and classifying each span as invention, mischaracterization, OCR error, miscounting, or other. Our system combines ModernBERT-large with frozen SigLIP2 patch features at 224\times224 and 384\times384 resolutions. A primary cross-modal detector produces token-level predictions, while a high-resolution branch adds bounded grounding and anchor-preserving residual corrections. The system uses only the official English training data and publicly available pretrained backbones, without retrieval, generated captions, external OCR, or additional labeled data. Post-hoc ablations show that the anchor-preserving correction provides the clearest incremental gain, while mismatched-image supervision has negligible development impact and histogram calibration is not beneficial. The submitted system achieves 0.2942 Cor and 0.2140 Cor+Lbl on the public leaderboard.</abstract>
<identifier type="citekey">vo-2026-team</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.44/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>715</start>
<end>721</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team HalluciNauts at SHROOM-Visions: Anchor-Preserving Dual-Resolution Grounding for Fine-Grained Vision Hallucination Detection
%A Vo, Khang Nhat Hoang
%Y Aziz, Wilker
%Y Berant, Jonathan
%Y Eikema, Bryan
%Y Ilia, Evgenia
%Y de Marneffe, Marie-Catherine
%Y Plank, Barbara
%Y Shelmanov, Artem
%Y Swayamdipta, Swabha
%Y Tiedemann, Jörg
%Y Vazhentsev, Artem
%Y Vázquez, Raúl
%Y Zerva, Chrysoula
%S The Proceedings of the Third Workshop on Uncertainty-Aware NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-486-6
%F vo-2026-team
%X We describe our submission to the SHROOM-Visions 2026 English task, which requires detecting hallucinated character spans in image-conditioned responses, assigning confidence scores, and classifying each span as invention, mischaracterization, OCR error, miscounting, or other. Our system combines ModernBERT-large with frozen SigLIP2 patch features at 224\times224 and 384\times384 resolutions. A primary cross-modal detector produces token-level predictions, while a high-resolution branch adds bounded grounding and anchor-preserving residual corrections. The system uses only the official English training data and publicly available pretrained backbones, without retrieval, generated captions, external OCR, or additional labeled data. Post-hoc ablations show that the anchor-preserving correction provides the clearest incremental gain, while mismatched-image supervision has negligible development impact and histogram calibration is not beneficial. The submitted system achieves 0.2942 Cor and 0.2140 Cor+Lbl on the public leaderboard.
%U https://aclanthology.org/2026.uncertainlp-main.44/
%P 715-721
Markdown (Informal)
[Team HalluciNauts at SHROOM-Visions: Anchor-Preserving Dual-Resolution Grounding for Fine-Grained Vision Hallucination Detection](https://aclanthology.org/2026.uncertainlp-main.44/) (Vo, UncertaiNLP 2026)
ACL