@inproceedings{mikhail-etal-2026-sckwoky,
title = "Sckwoky at {SHROOM}-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned {VLM}s via Dual-Prompted {L}o{RA} Decoders",
author = "Mikhail, Kulakov and
Solikhov, Ruslan and
Bondarenko, Ivan",
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.61/",
pages = "849--855",
ISBN = "979-8-89176-486-6",
abstract = "We present our system for the SHROOM-visions 2026 shared task on character-level hallucination span detection in image-conditioned vision-language model (VLM) responses, evaluated across English, French, Italian, and Chinese. The detector is built on a frozen Gemma-4-12B-it backbone with trainable LoRA adapters ($\sim$10.7M parameters). Because the backbone is a causal decoder, hidden states read from a single copy of an answer cannot attend to subsequent tokens; we therefore repeat the candidate answer within one prompt and extract features from its second occurrence, giving every position approximate bidirectional context in a single non-autoregressive pass. A character-level locator combines intermediate hidden states to predict hallucination probabilities, BIO boundaries, and a response-level abstention score, while separate language-specific classifiers assign one of five hallucination types to each predicted span. On the closed test set, our system reaches a macro-averaged character IoU of 0.4400, roughly doubling the official baseline (0.1850), and ranks 5th{--}6th on IoU across the four languages. In deployments where the same Gemma-4-12B-it model also generates answers, its base weights can be reused, making the approach practical for local question-answering systems that cannot run a separate verifier."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mikhail-etal-2026-sckwoky">
<titleInfo>
<title>Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned VLMs via Dual-Prompted LoRA Decoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kulakov</namePart>
<namePart type="family">Mikhail</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Solikhov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Bondarenko</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 present our system for the SHROOM-visions 2026 shared task on character-level hallucination span detection in image-conditioned vision-language model (VLM) responses, evaluated across English, French, Italian, and Chinese. The detector is built on a frozen Gemma-4-12B-it backbone with trainable LoRA adapters (\sim10.7M parameters). Because the backbone is a causal decoder, hidden states read from a single copy of an answer cannot attend to subsequent tokens; we therefore repeat the candidate answer within one prompt and extract features from its second occurrence, giving every position approximate bidirectional context in a single non-autoregressive pass. A character-level locator combines intermediate hidden states to predict hallucination probabilities, BIO boundaries, and a response-level abstention score, while separate language-specific classifiers assign one of five hallucination types to each predicted span. On the closed test set, our system reaches a macro-averaged character IoU of 0.4400, roughly doubling the official baseline (0.1850), and ranks 5th–6th on IoU across the four languages. In deployments where the same Gemma-4-12B-it model also generates answers, its base weights can be reused, making the approach practical for local question-answering systems that cannot run a separate verifier.</abstract>
<identifier type="citekey">mikhail-etal-2026-sckwoky</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.61/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>849</start>
<end>855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned VLMs via Dual-Prompted LoRA Decoders
%A Mikhail, Kulakov
%A Solikhov, Ruslan
%A Bondarenko, Ivan
%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 mikhail-etal-2026-sckwoky
%X We present our system for the SHROOM-visions 2026 shared task on character-level hallucination span detection in image-conditioned vision-language model (VLM) responses, evaluated across English, French, Italian, and Chinese. The detector is built on a frozen Gemma-4-12B-it backbone with trainable LoRA adapters (\sim10.7M parameters). Because the backbone is a causal decoder, hidden states read from a single copy of an answer cannot attend to subsequent tokens; we therefore repeat the candidate answer within one prompt and extract features from its second occurrence, giving every position approximate bidirectional context in a single non-autoregressive pass. A character-level locator combines intermediate hidden states to predict hallucination probabilities, BIO boundaries, and a response-level abstention score, while separate language-specific classifiers assign one of five hallucination types to each predicted span. On the closed test set, our system reaches a macro-averaged character IoU of 0.4400, roughly doubling the official baseline (0.1850), and ranks 5th–6th on IoU across the four languages. In deployments where the same Gemma-4-12B-it model also generates answers, its base weights can be reused, making the approach practical for local question-answering systems that cannot run a separate verifier.
%U https://aclanthology.org/2026.uncertainlp-main.61/
%P 849-855
Markdown (Informal)
[Sckwoky at SHROOM-Visions: Character-Level Hallucination-Span Detection in Image-Conditioned VLMs via Dual-Prompted LoRA Decoders](https://aclanthology.org/2026.uncertainlp-main.61/) (Mikhail et al., UncertaiNLP 2026)
ACL