@inproceedings{jo-shin-2026-multilingual,
title = "How does Multilingual Finetuning of Instruction-Tuned Large Language Models Affect Languages in Layer-Wise Hidden Representations?",
author = "Jo, Hyemi and
Shin, Hyopil",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.176/",
pages = "3703--3719",
ISBN = "979-8-89176-462-0",
abstract = "Contemporary large language models (LLMs) exhibit multilingual capabilities but remain predominantly English-centric, resulting in a persistent performance gap across languages. While some approaches to multilingual training are grounded in the implicit pivot language hypothesis to improve interpretability, it remains underexplored how the languages represented in each layer are affected during training, particularly in practical, cost-efficient instruction-tuning scenarios. In this study, we investigate how instruction tuning with Low-Rank Adaptation (LoRA) in a target language affects the layer-wise language representation of instruction-tuned LLMs, with the aim of assessing the relevance of the implicit pivot language hypothesis as a theoretical grounding for multilingual finetuning. We find that target-language instruction tuning shifts models' internal language representation in a non-uniform manner across layers and sublayers: middle layers shift further toward English, while early and final layers primarily serve the mapping between the target language and the dominant intermediate language. Our findings empirically support the implicit pivot language hypothesis in the context of instruction tuning, demonstrating that layer-wise parameter variation broadly corresponds to the hypothesized functional roles of layers in multilingual processing. Our code is available at: https://github.com/hyemijo/layer{\_}interpretability"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jo-shin-2026-multilingual">
<titleInfo>
<title>How does Multilingual Finetuning of Instruction-Tuned Large Language Models Affect Languages in Layer-Wise Hidden Representations?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hyemi</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyopil</namePart>
<namePart type="family">Shin</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Contemporary large language models (LLMs) exhibit multilingual capabilities but remain predominantly English-centric, resulting in a persistent performance gap across languages. While some approaches to multilingual training are grounded in the implicit pivot language hypothesis to improve interpretability, it remains underexplored how the languages represented in each layer are affected during training, particularly in practical, cost-efficient instruction-tuning scenarios. In this study, we investigate how instruction tuning with Low-Rank Adaptation (LoRA) in a target language affects the layer-wise language representation of instruction-tuned LLMs, with the aim of assessing the relevance of the implicit pivot language hypothesis as a theoretical grounding for multilingual finetuning. We find that target-language instruction tuning shifts models’ internal language representation in a non-uniform manner across layers and sublayers: middle layers shift further toward English, while early and final layers primarily serve the mapping between the target language and the dominant intermediate language. Our findings empirically support the implicit pivot language hypothesis in the context of instruction tuning, demonstrating that layer-wise parameter variation broadly corresponds to the hypothesized functional roles of layers in multilingual processing. Our code is available at: https://github.com/hyemijo/layer_interpretability</abstract>
<identifier type="citekey">jo-shin-2026-multilingual</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.176/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3703</start>
<end>3719</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How does Multilingual Finetuning of Instruction-Tuned Large Language Models Affect Languages in Layer-Wise Hidden Representations?
%A Jo, Hyemi
%A Shin, Hyopil
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F jo-shin-2026-multilingual
%X Contemporary large language models (LLMs) exhibit multilingual capabilities but remain predominantly English-centric, resulting in a persistent performance gap across languages. While some approaches to multilingual training are grounded in the implicit pivot language hypothesis to improve interpretability, it remains underexplored how the languages represented in each layer are affected during training, particularly in practical, cost-efficient instruction-tuning scenarios. In this study, we investigate how instruction tuning with Low-Rank Adaptation (LoRA) in a target language affects the layer-wise language representation of instruction-tuned LLMs, with the aim of assessing the relevance of the implicit pivot language hypothesis as a theoretical grounding for multilingual finetuning. We find that target-language instruction tuning shifts models’ internal language representation in a non-uniform manner across layers and sublayers: middle layers shift further toward English, while early and final layers primarily serve the mapping between the target language and the dominant intermediate language. Our findings empirically support the implicit pivot language hypothesis in the context of instruction tuning, demonstrating that layer-wise parameter variation broadly corresponds to the hypothesized functional roles of layers in multilingual processing. Our code is available at: https://github.com/hyemijo/layer_interpretability
%U https://aclanthology.org/2026.findings-emnlp.176/
%P 3703-3719
Markdown (Informal)
[How does Multilingual Finetuning of Instruction-Tuned Large Language Models Affect Languages in Layer-Wise Hidden Representations?](https://aclanthology.org/2026.findings-emnlp.176/) (Jo & Shin, Findings 2026)
ACL