@inproceedings{jeong-etal-2026-caml,
title = "{CAML} at {SHROOM}-Visions: Competency-Aware Intermediate-Layer Readouts for Multilingual Hallucination Localization",
author = "Jeong, Jiwon and
Yun, Kimin and
Bae, Yuseok",
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.48/",
pages = "743--749",
ISBN = "979-8-89176-486-6",
abstract = "We present CAML for multilingual hallucination localization at character level in SHROOM-Visions 2026. The system combines intermediate hidden states and four uncertainty features from a frozen Qwen3.5-4B evaluator, mapping supplied responses to character probabilities and five error categories. Probes from five cross-validation folds use temperature scaling and probability averaging, with about 3.37M trainable parameters in total. We compare readout depths under a common training and evaluation protocol. Selection on validation yields fixed layer 19, with macro character IoU of 0.3704; bootstrap intervals do not resolve its small differences from adjacent depth policies. Separately, the official challenge summary for the team gives macro IoU of 0.3825 and Spearman correlation of 0.4670, averaged over four languages. Independently trained Gemma probes also support localization, with fixed L24 scoring above both tested Gemma submissions combining layers. Across backbones, a single intermediate-layer readout consistently proves effective for localization, although the best depth remains backbone-specific rather than universal."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeong-etal-2026-caml">
<titleInfo>
<title>CAML at SHROOM-Visions: Competency-Aware Intermediate-Layer Readouts for Multilingual Hallucination Localization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiwon</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kimin</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuseok</namePart>
<namePart type="family">Bae</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 CAML for multilingual hallucination localization at character level in SHROOM-Visions 2026. The system combines intermediate hidden states and four uncertainty features from a frozen Qwen3.5-4B evaluator, mapping supplied responses to character probabilities and five error categories. Probes from five cross-validation folds use temperature scaling and probability averaging, with about 3.37M trainable parameters in total. We compare readout depths under a common training and evaluation protocol. Selection on validation yields fixed layer 19, with macro character IoU of 0.3704; bootstrap intervals do not resolve its small differences from adjacent depth policies. Separately, the official challenge summary for the team gives macro IoU of 0.3825 and Spearman correlation of 0.4670, averaged over four languages. Independently trained Gemma probes also support localization, with fixed L24 scoring above both tested Gemma submissions combining layers. Across backbones, a single intermediate-layer readout consistently proves effective for localization, although the best depth remains backbone-specific rather than universal.</abstract>
<identifier type="citekey">jeong-etal-2026-caml</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.48/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>743</start>
<end>749</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAML at SHROOM-Visions: Competency-Aware Intermediate-Layer Readouts for Multilingual Hallucination Localization
%A Jeong, Jiwon
%A Yun, Kimin
%A Bae, Yuseok
%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 jeong-etal-2026-caml
%X We present CAML for multilingual hallucination localization at character level in SHROOM-Visions 2026. The system combines intermediate hidden states and four uncertainty features from a frozen Qwen3.5-4B evaluator, mapping supplied responses to character probabilities and five error categories. Probes from five cross-validation folds use temperature scaling and probability averaging, with about 3.37M trainable parameters in total. We compare readout depths under a common training and evaluation protocol. Selection on validation yields fixed layer 19, with macro character IoU of 0.3704; bootstrap intervals do not resolve its small differences from adjacent depth policies. Separately, the official challenge summary for the team gives macro IoU of 0.3825 and Spearman correlation of 0.4670, averaged over four languages. Independently trained Gemma probes also support localization, with fixed L24 scoring above both tested Gemma submissions combining layers. Across backbones, a single intermediate-layer readout consistently proves effective for localization, although the best depth remains backbone-specific rather than universal.
%U https://aclanthology.org/2026.uncertainlp-main.48/
%P 743-749
Markdown (Informal)
[CAML at SHROOM-Visions: Competency-Aware Intermediate-Layer Readouts for Multilingual Hallucination Localization](https://aclanthology.org/2026.uncertainlp-main.48/) (Jeong et al., UncertaiNLP 2026)
ACL