@inproceedings{miranda-etal-2026-cross,
title = "Cross-Lingual Transfer and Shared Geometry of Deception Probes in {LLM}s",
author = "Miranda, Matheus Prado and
Locatelli, Marcelo Sartori and
Almeida, Virgilio and
Jr., Wagner Meira",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.33/",
pages = "404--421",
ISBN = "979-8-89176-469-9",
abstract = "Linear probes can recover deception-related signals from large language model activations, but existing evidence is overwhelmingly English-centric. We investigate whether this discrimination transfers across languages and what representational geometry accompanies such transfer. We train instructed-deception probes on controlled honest/deceptive instruction contrasts in English, Portuguese, Spanish, German, and Chinese, and evaluate them without target-language refitting on a multilingual adaptation of DeceptionBench across five models spanning four different families. Cross-language performance remains close to matched-language baselines, with all models satisfying our prespecified noninferiority criterion, although absolute discrimination varies substantially across models. We also find that language-specific probe directions are strongly aligned and concentrate around a shared consensus direction, while response representations retain clear language-specific organization. Additional construct-validity analyses show that measurable response-level cues, including style, sentiment, factual truthfulness, and length, explain part but not all of the strongest probe discrimination. These findings together suggest that cross-lingual transfer and shared probe geometry can coexist with model-dependent detection quality and persistent language structure, indicating that representational alignment alone is insufficient evidence of reliable multilingual deception monitoring."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miranda-etal-2026-cross">
<titleInfo>
<title>Cross-Lingual Transfer and Shared Geometry of Deception Probes in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matheus</namePart>
<namePart type="given">Prado</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcelo</namePart>
<namePart type="given">Sartori</namePart>
<namePart type="family">Locatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Virgilio</namePart>
<namePart type="family">Almeida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wagner</namePart>
<namePart type="given">Meira</namePart>
<namePart type="family">Jr.</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>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</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">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Linear probes can recover deception-related signals from large language model activations, but existing evidence is overwhelmingly English-centric. We investigate whether this discrimination transfers across languages and what representational geometry accompanies such transfer. We train instructed-deception probes on controlled honest/deceptive instruction contrasts in English, Portuguese, Spanish, German, and Chinese, and evaluate them without target-language refitting on a multilingual adaptation of DeceptionBench across five models spanning four different families. Cross-language performance remains close to matched-language baselines, with all models satisfying our prespecified noninferiority criterion, although absolute discrimination varies substantially across models. We also find that language-specific probe directions are strongly aligned and concentrate around a shared consensus direction, while response representations retain clear language-specific organization. Additional construct-validity analyses show that measurable response-level cues, including style, sentiment, factual truthfulness, and length, explain part but not all of the strongest probe discrimination. These findings together suggest that cross-lingual transfer and shared probe geometry can coexist with model-dependent detection quality and persistent language structure, indicating that representational alignment alone is insufficient evidence of reliable multilingual deception monitoring.</abstract>
<identifier type="citekey">miranda-etal-2026-cross</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.33/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>404</start>
<end>421</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Transfer and Shared Geometry of Deception Probes in LLMs
%A Miranda, Matheus Prado
%A Locatelli, Marcelo Sartori
%A Almeida, Virgilio
%A Jr., Wagner Meira
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F miranda-etal-2026-cross
%X Linear probes can recover deception-related signals from large language model activations, but existing evidence is overwhelmingly English-centric. We investigate whether this discrimination transfers across languages and what representational geometry accompanies such transfer. We train instructed-deception probes on controlled honest/deceptive instruction contrasts in English, Portuguese, Spanish, German, and Chinese, and evaluate them without target-language refitting on a multilingual adaptation of DeceptionBench across five models spanning four different families. Cross-language performance remains close to matched-language baselines, with all models satisfying our prespecified noninferiority criterion, although absolute discrimination varies substantially across models. We also find that language-specific probe directions are strongly aligned and concentrate around a shared consensus direction, while response representations retain clear language-specific organization. Additional construct-validity analyses show that measurable response-level cues, including style, sentiment, factual truthfulness, and length, explain part but not all of the strongest probe discrimination. These findings together suggest that cross-lingual transfer and shared probe geometry can coexist with model-dependent detection quality and persistent language structure, indicating that representational alignment alone is insufficient evidence of reliable multilingual deception monitoring.
%U https://aclanthology.org/2026.mrl-1.33/
%P 404-421
Markdown (Informal)
[Cross-Lingual Transfer and Shared Geometry of Deception Probes in LLMs](https://aclanthology.org/2026.mrl-1.33/) (Miranda et al., MRL 2026)
ACL