@inproceedings{ilinykh-szawerna-2025-need,
title = "``{I} Need More Context and an {E}nglish Translation'': Analysing How {LLM}s Identify Personal Information in {K}omi, {P}olish, and {E}nglish",
author = "Ilinykh, Nikolai and
Szawerna, Maria Irena",
editor = "Holdt, {\v{S}}pela Arhar and
Ilinykh, Nikolai and
Scalvini, Barbara and
Bruton, Micaella and
Debess, Iben Nyholm and
Tudor, Crina Madalina",
booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library, Estonia",
url = "https://aclanthology.org/2025.resourceful-1.32/",
pages = "165--178",
ISBN = "978-9908-53-121-2",
abstract = "Automatic identification of personal information (PI) is particularly difficult for languages with limited linguistic resources. Recently, large language models (LLMs) have been applied to various tasks involving low-resourced languages, but their capability to process PI in such contexts remains under-explored. In this paper we provide a qualitative analysis of the outputs from three LLMs prompted to identify PI in texts written in Komi (Permyak and Zyrian), Polish, and English. Our analysis highlights challenges in using pre-trained LLMs for PI identification in both low- and medium-resourced languages. It also motivates the need to develop LLMs that understand the differences in how PI is expressed across languages with varying levels of availability of linguistic resources."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ilinykh-szawerna-2025-need">
<titleInfo>
<title>“I Need More Context and an English Translation”: Analysing How LLMs Identify Personal Information in Komi, Polish, and English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="given">Arhar</namePart>
<namePart type="family">Holdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaella</namePart>
<namePart type="family">Bruton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="given">Madalina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library, Estonia</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-121-2</identifier>
</relatedItem>
<abstract>Automatic identification of personal information (PI) is particularly difficult for languages with limited linguistic resources. Recently, large language models (LLMs) have been applied to various tasks involving low-resourced languages, but their capability to process PI in such contexts remains under-explored. In this paper we provide a qualitative analysis of the outputs from three LLMs prompted to identify PI in texts written in Komi (Permyak and Zyrian), Polish, and English. Our analysis highlights challenges in using pre-trained LLMs for PI identification in both low- and medium-resourced languages. It also motivates the need to develop LLMs that understand the differences in how PI is expressed across languages with varying levels of availability of linguistic resources.</abstract>
<identifier type="citekey">ilinykh-szawerna-2025-need</identifier>
<location>
<url>https://aclanthology.org/2025.resourceful-1.32/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>165</start>
<end>178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T “I Need More Context and an English Translation”: Analysing How LLMs Identify Personal Information in Komi, Polish, and English
%A Ilinykh, Nikolai
%A Szawerna, Maria Irena
%Y Holdt, Špela Arhar
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Bruton, Micaella
%Y Debess, Iben Nyholm
%Y Tudor, Crina Madalina
%S Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)
%D 2025
%8 March
%I University of Tartu Library, Estonia
%C Tallinn, Estonia
%@ 978-9908-53-121-2
%F ilinykh-szawerna-2025-need
%X Automatic identification of personal information (PI) is particularly difficult for languages with limited linguistic resources. Recently, large language models (LLMs) have been applied to various tasks involving low-resourced languages, but their capability to process PI in such contexts remains under-explored. In this paper we provide a qualitative analysis of the outputs from three LLMs prompted to identify PI in texts written in Komi (Permyak and Zyrian), Polish, and English. Our analysis highlights challenges in using pre-trained LLMs for PI identification in both low- and medium-resourced languages. It also motivates the need to develop LLMs that understand the differences in how PI is expressed across languages with varying levels of availability of linguistic resources.
%U https://aclanthology.org/2025.resourceful-1.32/
%P 165-178
Markdown (Informal)
[“I Need More Context and an English Translation”: Analysing How LLMs Identify Personal Information in Komi, Polish, and English](https://aclanthology.org/2025.resourceful-1.32/) (Ilinykh & Szawerna, RESOURCEFUL 2025)
ACL