@inproceedings{behera-2026-l1cache,
title = "{L}1cache at {SHROOM}-Visions: {M}yco{G}ate-{VL} for Scorer-Aware Multilingual Hallucination Detection",
author = "Behera, Aman",
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.55/",
pages = "806--815",
ISBN = "979-8-89176-486-6",
abstract = "SHROOM-Visions 2026 asks systems to locate and categorize hallucinated spans in multilingual vision-language responses. We describe MycoGate-VL, which ranks characters with a mainly text-based multilingual detector ensemble, labels them with a vision-trained category head, abstains on likely clean documents with a learned gate, and orders its output spans to match how the released scorer rebuilds character probabilities. On the official final leaderboard our per-language submissions reach mean COR .378 and COR+LBL .274, about .2 below the top systems; no ZH IoU is available because that submission{'}s predictions were not available for the IoU scoring added later. Across our leaderboard submissions, most of the COR+LBL rise from .05 to .25 arrived with changes to output construction (per-category spans, clean-document routing, and span ordering), although these steps were bundled with model updates. The ordering step alone changes no model predictions. On our held-out split the system beats the mark-nothing and kit baselines on COR in every language but not on COR+LBL for English and Chinese. Zero-shot uncertainty, judging, and retrieval did not improve performance in our small-scale pilots, whereas a vision-trained category head did. Our central finding is that output encoding and abstention policy can substantially affect performance alongside the underlying detector, although closing the gap to the top systems requires better detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="behera-2026-l1cache">
<titleInfo>
<title>L1cache at SHROOM-Visions: MycoGate-VL for Scorer-Aware Multilingual Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Behera</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 locate and categorize hallucinated spans in multilingual vision-language responses. We describe MycoGate-VL, which ranks characters with a mainly text-based multilingual detector ensemble, labels them with a vision-trained category head, abstains on likely clean documents with a learned gate, and orders its output spans to match how the released scorer rebuilds character probabilities. On the official final leaderboard our per-language submissions reach mean COR .378 and COR+LBL .274, about .2 below the top systems; no ZH IoU is available because that submission’s predictions were not available for the IoU scoring added later. Across our leaderboard submissions, most of the COR+LBL rise from .05 to .25 arrived with changes to output construction (per-category spans, clean-document routing, and span ordering), although these steps were bundled with model updates. The ordering step alone changes no model predictions. On our held-out split the system beats the mark-nothing and kit baselines on COR in every language but not on COR+LBL for English and Chinese. Zero-shot uncertainty, judging, and retrieval did not improve performance in our small-scale pilots, whereas a vision-trained category head did. Our central finding is that output encoding and abstention policy can substantially affect performance alongside the underlying detector, although closing the gap to the top systems requires better detection.</abstract>
<identifier type="citekey">behera-2026-l1cache</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.55/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>806</start>
<end>815</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T L1cache at SHROOM-Visions: MycoGate-VL for Scorer-Aware Multilingual Hallucination Detection
%A Behera, Aman
%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 behera-2026-l1cache
%X SHROOM-Visions 2026 asks systems to locate and categorize hallucinated spans in multilingual vision-language responses. We describe MycoGate-VL, which ranks characters with a mainly text-based multilingual detector ensemble, labels them with a vision-trained category head, abstains on likely clean documents with a learned gate, and orders its output spans to match how the released scorer rebuilds character probabilities. On the official final leaderboard our per-language submissions reach mean COR .378 and COR+LBL .274, about .2 below the top systems; no ZH IoU is available because that submission’s predictions were not available for the IoU scoring added later. Across our leaderboard submissions, most of the COR+LBL rise from .05 to .25 arrived with changes to output construction (per-category spans, clean-document routing, and span ordering), although these steps were bundled with model updates. The ordering step alone changes no model predictions. On our held-out split the system beats the mark-nothing and kit baselines on COR in every language but not on COR+LBL for English and Chinese. Zero-shot uncertainty, judging, and retrieval did not improve performance in our small-scale pilots, whereas a vision-trained category head did. Our central finding is that output encoding and abstention policy can substantially affect performance alongside the underlying detector, although closing the gap to the top systems requires better detection.
%U https://aclanthology.org/2026.uncertainlp-main.55/
%P 806-815
Markdown (Informal)
[L1cache at SHROOM-Visions: MycoGate-VL for Scorer-Aware Multilingual Hallucination Detection](https://aclanthology.org/2026.uncertainlp-main.55/) (Behera, UncertaiNLP 2026)
ACL