@inproceedings{srivastava-etal-2026-team,
title = "Team {CPS} Lab at {SHROOM}-Visions: Parameter-Efficient Vision-Language Hallucination Detection with Threshold Tuning",
author = "Srivastava, Anika and
Kumar, Vishal and
Sharma, Harshita and
Aggarwal, Nitisha and
Jain Saxena, Geetika and
Pundir, Amit and
Singh, Sanjeev",
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.58/",
pages = "828--833",
ISBN = "979-8-89176-486-6",
abstract = "Fine-grained large-vision-language hallucination detection presents the challenge of locating hallucinated content in image-grounded responses and classifying them with corresponding hallucination categories. Our method for the SHROOM-Visions 2026 Shared Task explores a parameter-efficient solution by fine-tuning a lightweight token-level classification head on the frozen weights of the Qwen3-VL-8B-Instruct vision-language model. We utilized category-specific thresholds calculated based on validation character-level IoU and designed a span merging post-processing step to facilitate span localization with fewer fragmented predictions. We also establish a possible connection between the annotator agreement and the operating thresholds. Our analysis suggests that, within our experimental setup, hallucination categories that had higher inter-annotator agreement tended to have higher optimal decision thresholds whereas categories with lower agreement tended to have lower optimal decision thresholds. Our parameter-efficient method achieved ranks 18th, 16th, 16th, and 15th place on the English, French, Italian, and Chinese tracks, respectively, showing promising performance for multilingual fine-grained hallucination detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="srivastava-etal-2026-team">
<titleInfo>
<title>Team CPS Lab at SHROOM-Visions: Parameter-Efficient Vision-Language Hallucination Detection with Threshold Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anika</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishal</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshita</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitisha</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geetika</namePart>
<namePart type="family">Jain Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Pundir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Singh</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>Fine-grained large-vision-language hallucination detection presents the challenge of locating hallucinated content in image-grounded responses and classifying them with corresponding hallucination categories. Our method for the SHROOM-Visions 2026 Shared Task explores a parameter-efficient solution by fine-tuning a lightweight token-level classification head on the frozen weights of the Qwen3-VL-8B-Instruct vision-language model. We utilized category-specific thresholds calculated based on validation character-level IoU and designed a span merging post-processing step to facilitate span localization with fewer fragmented predictions. We also establish a possible connection between the annotator agreement and the operating thresholds. Our analysis suggests that, within our experimental setup, hallucination categories that had higher inter-annotator agreement tended to have higher optimal decision thresholds whereas categories with lower agreement tended to have lower optimal decision thresholds. Our parameter-efficient method achieved ranks 18th, 16th, 16th, and 15th place on the English, French, Italian, and Chinese tracks, respectively, showing promising performance for multilingual fine-grained hallucination detection.</abstract>
<identifier type="citekey">srivastava-etal-2026-team</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.58/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>828</start>
<end>833</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team CPS Lab at SHROOM-Visions: Parameter-Efficient Vision-Language Hallucination Detection with Threshold Tuning
%A Srivastava, Anika
%A Kumar, Vishal
%A Sharma, Harshita
%A Aggarwal, Nitisha
%A Jain Saxena, Geetika
%A Pundir, Amit
%A Singh, Sanjeev
%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 srivastava-etal-2026-team
%X Fine-grained large-vision-language hallucination detection presents the challenge of locating hallucinated content in image-grounded responses and classifying them with corresponding hallucination categories. Our method for the SHROOM-Visions 2026 Shared Task explores a parameter-efficient solution by fine-tuning a lightweight token-level classification head on the frozen weights of the Qwen3-VL-8B-Instruct vision-language model. We utilized category-specific thresholds calculated based on validation character-level IoU and designed a span merging post-processing step to facilitate span localization with fewer fragmented predictions. We also establish a possible connection between the annotator agreement and the operating thresholds. Our analysis suggests that, within our experimental setup, hallucination categories that had higher inter-annotator agreement tended to have higher optimal decision thresholds whereas categories with lower agreement tended to have lower optimal decision thresholds. Our parameter-efficient method achieved ranks 18th, 16th, 16th, and 15th place on the English, French, Italian, and Chinese tracks, respectively, showing promising performance for multilingual fine-grained hallucination detection.
%U https://aclanthology.org/2026.uncertainlp-main.58/
%P 828-833
Markdown (Informal)
[Team CPS Lab at SHROOM-Visions: Parameter-Efficient Vision-Language Hallucination Detection with Threshold Tuning](https://aclanthology.org/2026.uncertainlp-main.58/) (Srivastava et al., UncertaiNLP 2026)
ACL