@inproceedings{rattanajaratkul-etal-2026-smurfcat,
title = "{S}murf{C}at at {SHROOM}-Visions: Synthetic Augmentation for Multilingual Span-Level Hallucination Detection",
author = "Rattanajaratkul, Weerathep and
Panchenko, Alexander and
Rykov, Elisei",
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.53/",
pages = "789--796",
ISBN = "979-8-89176-486-6",
abstract = "In this paper, we present our system for the SHROOM-Visions shared task, which focuses on character-level hallucination localization and five-category classification in responses to image-grounded questions across four languages. We investigate a synthetic-data augmentation pipeline that combines annotator-agreement- and class-rarity-aware upsampling with controlled hallucination injection conditioned on image and response signals. We use the resulting data to fine-tune Qwen3-VL-8B-Instruct with LoRA to generate localized hallucination spans, confidence scores, and category labels as structured JSON. Conservative augmentation improves average validation IoU and Cor+Lbl over training on the original data, but outperforms the baseline on the test set only for Chinese, indicating substantial language-dependent effects. In the official Cor+Lbl ranking, our submissions placed 7th among 28 teams for English, 5th among 21 for French, 6th among 21 for Italian, and 5th among 22 for Chinese."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rattanajaratkul-etal-2026-smurfcat">
<titleInfo>
<title>SmurfCat at SHROOM-Visions: Synthetic Augmentation for Multilingual Span-Level Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weerathep</namePart>
<namePart type="family">Rattanajaratkul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisei</namePart>
<namePart type="family">Rykov</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>In this paper, we present our system for the SHROOM-Visions shared task, which focuses on character-level hallucination localization and five-category classification in responses to image-grounded questions across four languages. We investigate a synthetic-data augmentation pipeline that combines annotator-agreement- and class-rarity-aware upsampling with controlled hallucination injection conditioned on image and response signals. We use the resulting data to fine-tune Qwen3-VL-8B-Instruct with LoRA to generate localized hallucination spans, confidence scores, and category labels as structured JSON. Conservative augmentation improves average validation IoU and Cor+Lbl over training on the original data, but outperforms the baseline on the test set only for Chinese, indicating substantial language-dependent effects. In the official Cor+Lbl ranking, our submissions placed 7th among 28 teams for English, 5th among 21 for French, 6th among 21 for Italian, and 5th among 22 for Chinese.</abstract>
<identifier type="citekey">rattanajaratkul-etal-2026-smurfcat</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.53/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>789</start>
<end>796</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SmurfCat at SHROOM-Visions: Synthetic Augmentation for Multilingual Span-Level Hallucination Detection
%A Rattanajaratkul, Weerathep
%A Panchenko, Alexander
%A Rykov, Elisei
%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 rattanajaratkul-etal-2026-smurfcat
%X In this paper, we present our system for the SHROOM-Visions shared task, which focuses on character-level hallucination localization and five-category classification in responses to image-grounded questions across four languages. We investigate a synthetic-data augmentation pipeline that combines annotator-agreement- and class-rarity-aware upsampling with controlled hallucination injection conditioned on image and response signals. We use the resulting data to fine-tune Qwen3-VL-8B-Instruct with LoRA to generate localized hallucination spans, confidence scores, and category labels as structured JSON. Conservative augmentation improves average validation IoU and Cor+Lbl over training on the original data, but outperforms the baseline on the test set only for Chinese, indicating substantial language-dependent effects. In the official Cor+Lbl ranking, our submissions placed 7th among 28 teams for English, 5th among 21 for French, 6th among 21 for Italian, and 5th among 22 for Chinese.
%U https://aclanthology.org/2026.uncertainlp-main.53/
%P 789-796
Markdown (Informal)
[SmurfCat at SHROOM-Visions: Synthetic Augmentation for Multilingual Span-Level Hallucination Detection](https://aclanthology.org/2026.uncertainlp-main.53/) (Rattanajaratkul et al., UncertaiNLP 2026)
ACL