@inproceedings{yamin-etal-2026-dynamos-shroom,
title = "Dynamos at {SHROOM}-Visions: Metric-Aligned Token Tagging and Ensembles for Multilingual Vision-Language Hallucination-Span Detection",
author = "Yamin, Muhammad and
Wahid, Sheikh Abdul and
Arshad, Ali",
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.45/",
pages = "722--728",
ISBN = "979-8-89176-486-6",
abstract = "Vision-language models describe images fluently and, too often, wrongly. SHROOM-Visions 2026 asks systems to mark exactly which characters of such a description are hallucinated, and of what kind, in Chinese, English, French, and Italian. Working on this task we find that how a system reads predictions out of a model matters as much as which model it uses: the metric is a rank correlation against soft, multi-annotator labels, and aligning the prediction pipeline to it is worth as much as a larger encoder. We treat the problem as per-character sequence tagging. Starting from a fine-tuned XLM-RoBERTa tagger, we (i) formulate the task with one independent probability head per hallucination class, which matches the labelled and unlabelled correlation metrics; (ii) reconstruct spans in a way that respects the scorer{'}s tie-breaking behaviour; and (iii) tune per-class decision thresholds with cross-validated Bayesian search. These changes lift the score substantially with no change to the underlying model. Keeping this output layer fixed, we then compare encoders: a text-only tagger with added visual features, and a fine-tuned vision-language model. The vision-language model, adapted with low-rank updates and read out through the same five heads, is our strongest system in every language and improves most on the labelled score, which is the part of the task that needs the image. It also transfers cleanly from validation to test, in contrast to the tuned text ensembles, whose threshold choices overfit the validation split."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamin-etal-2026-dynamos-shroom">
<titleInfo>
<title>Dynamos at SHROOM-Visions: Metric-Aligned Token Tagging and Ensembles for Multilingual Vision-Language Hallucination-Span Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Yamin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheikh</namePart>
<namePart type="given">Abdul</namePart>
<namePart type="family">Wahid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Arshad</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>Vision-language models describe images fluently and, too often, wrongly. SHROOM-Visions 2026 asks systems to mark exactly which characters of such a description are hallucinated, and of what kind, in Chinese, English, French, and Italian. Working on this task we find that how a system reads predictions out of a model matters as much as which model it uses: the metric is a rank correlation against soft, multi-annotator labels, and aligning the prediction pipeline to it is worth as much as a larger encoder. We treat the problem as per-character sequence tagging. Starting from a fine-tuned XLM-RoBERTa tagger, we (i) formulate the task with one independent probability head per hallucination class, which matches the labelled and unlabelled correlation metrics; (ii) reconstruct spans in a way that respects the scorer’s tie-breaking behaviour; and (iii) tune per-class decision thresholds with cross-validated Bayesian search. These changes lift the score substantially with no change to the underlying model. Keeping this output layer fixed, we then compare encoders: a text-only tagger with added visual features, and a fine-tuned vision-language model. The vision-language model, adapted with low-rank updates and read out through the same five heads, is our strongest system in every language and improves most on the labelled score, which is the part of the task that needs the image. It also transfers cleanly from validation to test, in contrast to the tuned text ensembles, whose threshold choices overfit the validation split.</abstract>
<identifier type="citekey">yamin-etal-2026-dynamos-shroom</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.45/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>722</start>
<end>728</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dynamos at SHROOM-Visions: Metric-Aligned Token Tagging and Ensembles for Multilingual Vision-Language Hallucination-Span Detection
%A Yamin, Muhammad
%A Wahid, Sheikh Abdul
%A Arshad, Ali
%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 yamin-etal-2026-dynamos-shroom
%X Vision-language models describe images fluently and, too often, wrongly. SHROOM-Visions 2026 asks systems to mark exactly which characters of such a description are hallucinated, and of what kind, in Chinese, English, French, and Italian. Working on this task we find that how a system reads predictions out of a model matters as much as which model it uses: the metric is a rank correlation against soft, multi-annotator labels, and aligning the prediction pipeline to it is worth as much as a larger encoder. We treat the problem as per-character sequence tagging. Starting from a fine-tuned XLM-RoBERTa tagger, we (i) formulate the task with one independent probability head per hallucination class, which matches the labelled and unlabelled correlation metrics; (ii) reconstruct spans in a way that respects the scorer’s tie-breaking behaviour; and (iii) tune per-class decision thresholds with cross-validated Bayesian search. These changes lift the score substantially with no change to the underlying model. Keeping this output layer fixed, we then compare encoders: a text-only tagger with added visual features, and a fine-tuned vision-language model. The vision-language model, adapted with low-rank updates and read out through the same five heads, is our strongest system in every language and improves most on the labelled score, which is the part of the task that needs the image. It also transfers cleanly from validation to test, in contrast to the tuned text ensembles, whose threshold choices overfit the validation split.
%U https://aclanthology.org/2026.uncertainlp-main.45/
%P 722-728
Markdown (Informal)
[Dynamos at SHROOM-Visions: Metric-Aligned Token Tagging and Ensembles for Multilingual Vision-Language Hallucination-Span Detection](https://aclanthology.org/2026.uncertainlp-main.45/) (Yamin et al., UncertaiNLP 2026)
ACL