@inproceedings{goswami-etal-2025-multilingual,
title = "Multilingual Native Language Identification with Large Language Models",
author = "Goswami, Dhiman and
Zampieri, Marcos and
North, Kai and
Malmasi, Shervin and
Anastasopoulos, Antonios",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.19/",
doi = "10.18653/v1/2025.naacl-srw.19",
pages = "193--199",
ISBN = "979-8-89176-192-6",
abstract = "Native Language Identification (NLI) is the task of automatically identifying the native language (L1) of individuals based on their second language (L2) production. The introduction of Large Language Models (LLMs) with billions of parameters has renewed interest in text-based NLI, with new studies exploring LLM-based approaches to NLI on English L2. The capabilities of state-of-the-art LLMs on non-English NLI corpora, however, have not yet been fully evaluated. To fill this important gap, we present the first evaluation of LLMs for multilingual NLI. We evaluated the performance of several LLMs compared to traditional statistical machine learning models and language-specific BERT-based models on NLI corpora in English, Italian, Norwegian, and Portuguese. Our results show that fine-tuned GPT-4 models achieve state-of-the-art NLI performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goswami-etal-2025-multilingual">
<titleInfo>
<title>Multilingual Native Language Identification with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhiman</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>Native Language Identification (NLI) is the task of automatically identifying the native language (L1) of individuals based on their second language (L2) production. The introduction of Large Language Models (LLMs) with billions of parameters has renewed interest in text-based NLI, with new studies exploring LLM-based approaches to NLI on English L2. The capabilities of state-of-the-art LLMs on non-English NLI corpora, however, have not yet been fully evaluated. To fill this important gap, we present the first evaluation of LLMs for multilingual NLI. We evaluated the performance of several LLMs compared to traditional statistical machine learning models and language-specific BERT-based models on NLI corpora in English, Italian, Norwegian, and Portuguese. Our results show that fine-tuned GPT-4 models achieve state-of-the-art NLI performance.</abstract>
<identifier type="citekey">goswami-etal-2025-multilingual</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.19</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.19/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>193</start>
<end>199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Native Language Identification with Large Language Models
%A Goswami, Dhiman
%A Zampieri, Marcos
%A North, Kai
%A Malmasi, Shervin
%A Anastasopoulos, Antonios
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F goswami-etal-2025-multilingual
%X Native Language Identification (NLI) is the task of automatically identifying the native language (L1) of individuals based on their second language (L2) production. The introduction of Large Language Models (LLMs) with billions of parameters has renewed interest in text-based NLI, with new studies exploring LLM-based approaches to NLI on English L2. The capabilities of state-of-the-art LLMs on non-English NLI corpora, however, have not yet been fully evaluated. To fill this important gap, we present the first evaluation of LLMs for multilingual NLI. We evaluated the performance of several LLMs compared to traditional statistical machine learning models and language-specific BERT-based models on NLI corpora in English, Italian, Norwegian, and Portuguese. Our results show that fine-tuned GPT-4 models achieve state-of-the-art NLI performance.
%R 10.18653/v1/2025.naacl-srw.19
%U https://aclanthology.org/2025.naacl-srw.19/
%U https://doi.org/10.18653/v1/2025.naacl-srw.19
%P 193-199
Markdown (Informal)
[Multilingual Native Language Identification with Large Language Models](https://aclanthology.org/2025.naacl-srw.19/) (Goswami et al., NAACL 2025)
ACL
- Dhiman Goswami, Marcos Zampieri, Kai North, Shervin Malmasi, and Antonios Anastasopoulos. 2025. Multilingual Native Language Identification with Large Language Models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 193–199, Albuquerque, USA. Association for Computational Linguistics.