@inproceedings{fernandes-2026-usp-shroom,
title = "{USP} at {SHROOM}-Visions: Why Informative Proxy Visual Signals Do Not Localize Hallucinated Spans",
author = "Fernandes, Rafael M.",
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.47/",
pages = "734--742",
ISBN = "979-8-89176-486-6",
abstract = "SHROOM-Visions 2026 asks systems to mark the exact characters hallucinated in a vision{--}language model{'}s response. The generating model is withheld, so any model-derived signal is a proxy, and we ask whether it improves character-level localization. We first characterize the metric: span position dominates attainable Cor under the benchmark metric, and constant scores within a response give no ranking signal; an oracle sentence-level detector reaches Cor 0.476 where gold spans reach 0.970. Testing three proxy signals and one direct adjudication baseline, sentence-level signals add at most 0.002 Cor, as predicted. Representation shift is not explained by that account: a probe recovers a fine-grained signal across all four languages (macro AUROC 0.652) yet adds only +0.009. Its discrimination is uneven across error categories, strongest on smaller ones such as OCR errors, but reweighting that mixture accounts for at most 0.028 AUROC. The tested factors do not explain the remaining gap."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fernandes-2026-usp-shroom">
<titleInfo>
<title>USP at SHROOM-Visions: Why Informative Proxy Visual Signals Do Not Localize Hallucinated Spans</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Fernandes</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>SHROOM-Visions 2026 asks systems to mark the exact characters hallucinated in a vision–language model’s response. The generating model is withheld, so any model-derived signal is a proxy, and we ask whether it improves character-level localization. We first characterize the metric: span position dominates attainable Cor under the benchmark metric, and constant scores within a response give no ranking signal; an oracle sentence-level detector reaches Cor 0.476 where gold spans reach 0.970. Testing three proxy signals and one direct adjudication baseline, sentence-level signals add at most 0.002 Cor, as predicted. Representation shift is not explained by that account: a probe recovers a fine-grained signal across all four languages (macro AUROC 0.652) yet adds only +0.009. Its discrimination is uneven across error categories, strongest on smaller ones such as OCR errors, but reweighting that mixture accounts for at most 0.028 AUROC. The tested factors do not explain the remaining gap.</abstract>
<identifier type="citekey">fernandes-2026-usp-shroom</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.47/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>734</start>
<end>742</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T USP at SHROOM-Visions: Why Informative Proxy Visual Signals Do Not Localize Hallucinated Spans
%A Fernandes, Rafael M.
%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 fernandes-2026-usp-shroom
%X SHROOM-Visions 2026 asks systems to mark the exact characters hallucinated in a vision–language model’s response. The generating model is withheld, so any model-derived signal is a proxy, and we ask whether it improves character-level localization. We first characterize the metric: span position dominates attainable Cor under the benchmark metric, and constant scores within a response give no ranking signal; an oracle sentence-level detector reaches Cor 0.476 where gold spans reach 0.970. Testing three proxy signals and one direct adjudication baseline, sentence-level signals add at most 0.002 Cor, as predicted. Representation shift is not explained by that account: a probe recovers a fine-grained signal across all four languages (macro AUROC 0.652) yet adds only +0.009. Its discrimination is uneven across error categories, strongest on smaller ones such as OCR errors, but reweighting that mixture accounts for at most 0.028 AUROC. The tested factors do not explain the remaining gap.
%U https://aclanthology.org/2026.uncertainlp-main.47/
%P 734-742
Markdown (Informal)
[USP at SHROOM-Visions: Why Informative Proxy Visual Signals Do Not Localize Hallucinated Spans](https://aclanthology.org/2026.uncertainlp-main.47/) (Fernandes, UncertaiNLP 2026)
ACL