<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="auger-etal-2026-using">
    <titleInfo>
        <title>Using large language models to provide effective embeddings for native language identification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Roxane</namePart>
        <namePart type="family">Auger</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Olivier</namePart>
        <namePart type="family">Boeffard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-François</namePart>
        <namePart type="family">Bonastre</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>Native Language Identification (NLI) consists in predicting a person’s native language based on their second language production. In the field of text-based NLI, approaches based on Large Language Models (LLM) outperform previous approaches based on statistical classifiers trained on linguistic features. However, the unstructured nature of LLM textual output does not support the direct application of usual classifiers. To address this limitation, we explore the use of LLM to generate effective latent vector representations (embeddings) for NLI. Our experiments, across ten models ranging from 0.1B to 405B parameters, show that embeddings gathered from a frozen LLM coupled with a linear classifier match the performance of fine-tuned generative LLM. Furthermore, layer-depth analysis reveals that the first 40% of an LLM’s layers are sufficient to achieve full representational utility for NLI.</abstract>
    <identifier type="citekey">auger-etal-2026-using</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1251/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>26452</start>
            <end>26460</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Using large language models to provide effective embeddings for native language identification
%A Auger, Roxane
%A Boeffard, Olivier
%A Bonastre, Jean-François
%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 auger-etal-2026-using
%X Native Language Identification (NLI) consists in predicting a person’s native language based on their second language production. In the field of text-based NLI, approaches based on Large Language Models (LLM) outperform previous approaches based on statistical classifiers trained on linguistic features. However, the unstructured nature of LLM textual output does not support the direct application of usual classifiers. To address this limitation, we explore the use of LLM to generate effective latent vector representations (embeddings) for NLI. Our experiments, across ten models ranging from 0.1B to 405B parameters, show that embeddings gathered from a frozen LLM coupled with a linear classifier match the performance of fine-tuned generative LLM. Furthermore, layer-depth analysis reveals that the first 40% of an LLM’s layers are sufficient to achieve full representational utility for NLI.
%U https://aclanthology.org/2026.findings-emnlp.1251/
%P 26452-26460

Markdown (Informal)

[Using large language models to provide effective embeddings for native language identification](https://aclanthology.org/2026.findings-emnlp.1251/) (Auger et al., Findings 2026)

• Using large language models to provide effective embeddings for native language identification (Auger et al., Findings 2026)

ACL

• Roxane Auger, Olivier Boeffard, and Jean-François Bonastre. 2026. Using large language models to provide effective embeddings for native language identification. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 26452–26460, Budapest, Hungary. Association for Computational Linguistics.