@inproceedings{uvalieva-2026-leaving,
title = "Leaving the {E}nglish Basin: A Logit-Lens View of Cross-Lingual Emotion Transfer in Multilingual {LLM}s",
author = "Uvalieva, Zarina",
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-1.7/",
pages = "68--90",
ISBN = "979-8-89176-469-9",
abstract = "We study how multilingual LLMs encode emotion in English, Russian, and Kyrgyz - a low-resource Turkic language absent from prior emotion-probing work - on a parallel corpus of 1,480 sentences with six Ekman labels mapped from GoEmotions. Across four decoder LLMs (Gemma 4, Qwen3, Llama-3.1, Mistral), an encoder baseline (XLM-R), and an expanded 8-model sample, we combine layer-wise probing, similarity metrics (CKA, Procrustes, RSA), leakage-free cross-lingual transfer, and a null-calibrated sentence-level logit lens. Three findings. (1) What separates languages in the ``latent-English'' pivot (Wendler et al., 2024) is not the mid-network English level {---} which a shuffled-representation null reproduces - but the depth of the exit from the English basin: on pooled sentence representations Kyrgyz exits only in the last third of every applicable decoder (d{\_}{.5} {\ensuremath{\approx}} .97/.86/.97) and never earlier than Russian (.97/.64/.75; under a last-token lens both languages tie late, .92{--}.97) - a lossier pivot, consistent with its larger transfer gap. (2) Similarity and transfer dissociate: Mistral has the highest RU{--}KY CKA (.800) yet the lowest KY transfer (.239), so CKA is an unreliable proxy for cross-lingual generalization. (3) Encoder/decoder architecture does not order Kyrgyz transfer: XLM-R leads (.384) but mBERT is second-to-last (.198). XLM-R{'}s edge is not significant on absolute KY (p=.081); it concentrates in the into-Kyrgyz directions (interaction p{\ensuremath{<}}.01 vs. Qwen3) and reaches significance only under a secondary chance-corrected metric - consistent with pre-training data scale and domain rather than architecture (an interpretation, not a ranking predictor). All 8 models beat chance in every language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uvalieva-2026-leaving">
<titleInfo>
<title>Leaving the English Basin: A Logit-Lens View of Cross-Lingual Emotion Transfer in Multilingual LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zarina</namePart>
<namePart type="family">Uvalieva</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>We study how multilingual LLMs encode emotion in English, Russian, and Kyrgyz - a low-resource Turkic language absent from prior emotion-probing work - on a parallel corpus of 1,480 sentences with six Ekman labels mapped from GoEmotions. Across four decoder LLMs (Gemma 4, Qwen3, Llama-3.1, Mistral), an encoder baseline (XLM-R), and an expanded 8-model sample, we combine layer-wise probing, similarity metrics (CKA, Procrustes, RSA), leakage-free cross-lingual transfer, and a null-calibrated sentence-level logit lens. Three findings. (1) What separates languages in the “latent-English” pivot (Wendler et al., 2024) is not the mid-network English level — which a shuffled-representation null reproduces - but the depth of the exit from the English basin: on pooled sentence representations Kyrgyz exits only in the last third of every applicable decoder (d_.5 \ensuremath\approx .97/.86/.97) and never earlier than Russian (.97/.64/.75; under a last-token lens both languages tie late, .92–.97) - a lossier pivot, consistent with its larger transfer gap. (2) Similarity and transfer dissociate: Mistral has the highest RU–KY CKA (.800) yet the lowest KY transfer (.239), so CKA is an unreliable proxy for cross-lingual generalization. (3) Encoder/decoder architecture does not order Kyrgyz transfer: XLM-R leads (.384) but mBERT is second-to-last (.198). XLM-R’s edge is not significant on absolute KY (p=.081); it concentrates in the into-Kyrgyz directions (interaction p\ensuremath<.01 vs. Qwen3) and reaches significance only under a secondary chance-corrected metric - consistent with pre-training data scale and domain rather than architecture (an interpretation, not a ranking predictor). All 8 models beat chance in every language.</abstract>
<identifier type="citekey">uvalieva-2026-leaving</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.7/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>68</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leaving the English Basin: A Logit-Lens View of Cross-Lingual Emotion Transfer in Multilingual LLMs
%A Uvalieva, Zarina
%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 uvalieva-2026-leaving
%X We study how multilingual LLMs encode emotion in English, Russian, and Kyrgyz - a low-resource Turkic language absent from prior emotion-probing work - on a parallel corpus of 1,480 sentences with six Ekman labels mapped from GoEmotions. Across four decoder LLMs (Gemma 4, Qwen3, Llama-3.1, Mistral), an encoder baseline (XLM-R), and an expanded 8-model sample, we combine layer-wise probing, similarity metrics (CKA, Procrustes, RSA), leakage-free cross-lingual transfer, and a null-calibrated sentence-level logit lens. Three findings. (1) What separates languages in the “latent-English” pivot (Wendler et al., 2024) is not the mid-network English level — which a shuffled-representation null reproduces - but the depth of the exit from the English basin: on pooled sentence representations Kyrgyz exits only in the last third of every applicable decoder (d_.5 \ensuremath\approx .97/.86/.97) and never earlier than Russian (.97/.64/.75; under a last-token lens both languages tie late, .92–.97) - a lossier pivot, consistent with its larger transfer gap. (2) Similarity and transfer dissociate: Mistral has the highest RU–KY CKA (.800) yet the lowest KY transfer (.239), so CKA is an unreliable proxy for cross-lingual generalization. (3) Encoder/decoder architecture does not order Kyrgyz transfer: XLM-R leads (.384) but mBERT is second-to-last (.198). XLM-R’s edge is not significant on absolute KY (p=.081); it concentrates in the into-Kyrgyz directions (interaction p\ensuremath<.01 vs. Qwen3) and reaches significance only under a secondary chance-corrected metric - consistent with pre-training data scale and domain rather than architecture (an interpretation, not a ranking predictor). All 8 models beat chance in every language.
%U https://aclanthology.org/2026.mrl-1.7/
%P 68-90
Markdown (Informal)
[Leaving the English Basin: A Logit-Lens View of Cross-Lingual Emotion Transfer in Multilingual LLMs](https://aclanthology.org/2026.mrl-1.7/) (Uvalieva, MRL 2026)
ACL