@inproceedings{raut-2026-winnar749,
title = "{WINNAR}749 at {SHROOM}-Visions: Model-Agnostic Fine-Grained Hallucination Detection in {VLM}s via {QL}o{RA} Approach with Soft, Calibrated Targets",
author = "Raut, Ranjit",
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.54/",
pages = "797--805",
ISBN = "979-8-89176-486-6",
abstract = "Vision-Language Models (VLMs) are showing remarkable performance in connecting vision and language, closely intertwined. However, they are vulnerable to hallucination and alignment problems. To address these issues, this paper describes a simple system for the SHROOM-visions shared task on character-level hallucination detection in image-conditioned text. The system attaches two lightweight linear heads to a pretrained VLM backbone and fine-tunes them, together with low-rank adapters on the backbone. As a result, they predict a per-character hallucination probability and a per-character distribution over five hallucination classes. We train directly against soft targets as the released annotations are themselves soft (overlapping, disagreeing multi-annotator spans), rather than collapsing them into hard span labels and fit a post-hoc isotonic calibration map so that predicted probabilities track empirical annotator agreement, the quantity the task{'}s Confidence Calibration metric rewards. The system we submitted to the official shared-task evaluation built on Qwen2.5-VL-3B-Instruct contained two implementation issues that we identified only after the submission deadline; we report the official results as submitted, document the issues and their fixes, and separately report unofficial post-evaluation results obtained after correcting them and porting the pipeline to Qwen3.5-4B.[The code is available at {\ensuremath{<}}https://github.com/theranjitraut/SHROOM-Visions-2026{\ensuremath{>}}]"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="raut-2026-winnar749">
<titleInfo>
<title>WINNAR749 at SHROOM-Visions: Model-Agnostic Fine-Grained Hallucination Detection in VLMs via QLoRA Approach with Soft, Calibrated Targets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ranjit</namePart>
<namePart type="family">Raut</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 (VLMs) are showing remarkable performance in connecting vision and language, closely intertwined. However, they are vulnerable to hallucination and alignment problems. To address these issues, this paper describes a simple system for the SHROOM-visions shared task on character-level hallucination detection in image-conditioned text. The system attaches two lightweight linear heads to a pretrained VLM backbone and fine-tunes them, together with low-rank adapters on the backbone. As a result, they predict a per-character hallucination probability and a per-character distribution over five hallucination classes. We train directly against soft targets as the released annotations are themselves soft (overlapping, disagreeing multi-annotator spans), rather than collapsing them into hard span labels and fit a post-hoc isotonic calibration map so that predicted probabilities track empirical annotator agreement, the quantity the task’s Confidence Calibration metric rewards. The system we submitted to the official shared-task evaluation built on Qwen2.5-VL-3B-Instruct contained two implementation issues that we identified only after the submission deadline; we report the official results as submitted, document the issues and their fixes, and separately report unofficial post-evaluation results obtained after correcting them and porting the pipeline to Qwen3.5-4B.[The code is available at \ensuremath<https://github.com/theranjitraut/SHROOM-Visions-2026\ensuremath>]</abstract>
<identifier type="citekey">raut-2026-winnar749</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.54/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>797</start>
<end>805</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WINNAR749 at SHROOM-Visions: Model-Agnostic Fine-Grained Hallucination Detection in VLMs via QLoRA Approach with Soft, Calibrated Targets
%A Raut, Ranjit
%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 raut-2026-winnar749
%X Vision-Language Models (VLMs) are showing remarkable performance in connecting vision and language, closely intertwined. However, they are vulnerable to hallucination and alignment problems. To address these issues, this paper describes a simple system for the SHROOM-visions shared task on character-level hallucination detection in image-conditioned text. The system attaches two lightweight linear heads to a pretrained VLM backbone and fine-tunes them, together with low-rank adapters on the backbone. As a result, they predict a per-character hallucination probability and a per-character distribution over five hallucination classes. We train directly against soft targets as the released annotations are themselves soft (overlapping, disagreeing multi-annotator spans), rather than collapsing them into hard span labels and fit a post-hoc isotonic calibration map so that predicted probabilities track empirical annotator agreement, the quantity the task’s Confidence Calibration metric rewards. The system we submitted to the official shared-task evaluation built on Qwen2.5-VL-3B-Instruct contained two implementation issues that we identified only after the submission deadline; we report the official results as submitted, document the issues and their fixes, and separately report unofficial post-evaluation results obtained after correcting them and porting the pipeline to Qwen3.5-4B.[The code is available at \ensuremath<https://github.com/theranjitraut/SHROOM-Visions-2026\ensuremath>]
%U https://aclanthology.org/2026.uncertainlp-main.54/
%P 797-805
Markdown (Informal)
[WINNAR749 at SHROOM-Visions: Model-Agnostic Fine-Grained Hallucination Detection in VLMs via QLoRA Approach with Soft, Calibrated Targets](https://aclanthology.org/2026.uncertainlp-main.54/) (Raut, UncertaiNLP 2026)
ACL