@inproceedings{shehryar-2026-irums,
title = "Irums at {SHROOM}-Visions 2026: When One Fix Doesn{'}t Fit All {---} Category-Aware Hallucination Span Detection",
author = "Shehryar, Irum",
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.49/",
pages = "750--759",
ISBN = "979-8-89176-486-6",
abstract = "This paper describes our system for the English subset of the SHROOM-Visions 2026 shared task, which requires detecting hallucinated spans in vision-language model outputs across Chinese, English, French, and Italian, and labeling them into five categories. We used Claude Haiku 4.5 as a zero-shot detector, with post-processing relabeling and Sonnet 5-based second-opinion verification for select categories. Our final system achieved 0.3015 (Cor+Lbl), 0.3949 (Cor) and 0.3421 (IoU). Our error analysis found that missed detections, low annotator agreement, and unresolved overlap between the invention and mischaracterization categories account for the majority of remaining errors, with additional score loss when the model finds the right content but its flagged text is a different length than gold{'}s, or is labeled with the wrong category. Systematically testing and comparing individual approaches shows that none of the methods we tried is effective across all categories on its own; category-specific, targeted fixes improved performance more reliably than any single general-purpose mechanism we tested."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shehryar-2026-irums">
<titleInfo>
<title>Irums at SHROOM-Visions 2026: When One Fix Doesn’t Fit All — Category-Aware Hallucination Span Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irum</namePart>
<namePart type="family">Shehryar</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>This paper describes our system for the English subset of the SHROOM-Visions 2026 shared task, which requires detecting hallucinated spans in vision-language model outputs across Chinese, English, French, and Italian, and labeling them into five categories. We used Claude Haiku 4.5 as a zero-shot detector, with post-processing relabeling and Sonnet 5-based second-opinion verification for select categories. Our final system achieved 0.3015 (Cor+Lbl), 0.3949 (Cor) and 0.3421 (IoU). Our error analysis found that missed detections, low annotator agreement, and unresolved overlap between the invention and mischaracterization categories account for the majority of remaining errors, with additional score loss when the model finds the right content but its flagged text is a different length than gold’s, or is labeled with the wrong category. Systematically testing and comparing individual approaches shows that none of the methods we tried is effective across all categories on its own; category-specific, targeted fixes improved performance more reliably than any single general-purpose mechanism we tested.</abstract>
<identifier type="citekey">shehryar-2026-irums</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.49/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>750</start>
<end>759</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Irums at SHROOM-Visions 2026: When One Fix Doesn’t Fit All — Category-Aware Hallucination Span Detection
%A Shehryar, Irum
%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 shehryar-2026-irums
%X This paper describes our system for the English subset of the SHROOM-Visions 2026 shared task, which requires detecting hallucinated spans in vision-language model outputs across Chinese, English, French, and Italian, and labeling them into five categories. We used Claude Haiku 4.5 as a zero-shot detector, with post-processing relabeling and Sonnet 5-based second-opinion verification for select categories. Our final system achieved 0.3015 (Cor+Lbl), 0.3949 (Cor) and 0.3421 (IoU). Our error analysis found that missed detections, low annotator agreement, and unresolved overlap between the invention and mischaracterization categories account for the majority of remaining errors, with additional score loss when the model finds the right content but its flagged text is a different length than gold’s, or is labeled with the wrong category. Systematically testing and comparing individual approaches shows that none of the methods we tried is effective across all categories on its own; category-specific, targeted fixes improved performance more reliably than any single general-purpose mechanism we tested.
%U https://aclanthology.org/2026.uncertainlp-main.49/
%P 750-759
Markdown (Informal)
[Irums at SHROOM-Visions 2026: When One Fix Doesn’t Fit All — Category-Aware Hallucination Span Detection](https://aclanthology.org/2026.uncertainlp-main.49/) (Shehryar, UncertaiNLP 2026)
ACL