<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="szawerna-suchardt-2026-fill">
    <titleInfo>
        <title>Fill-in-the-Blanks: Automatic Generation and Evaluation of Language Models’ Pseudonyms for English and Swedish Texts</title>
    </titleInfo>
    <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>
    <name type="personal">
        <namePart type="given">Jacob</namePart>
        <namePart type="given">Lee</namePart>
        <namePart type="family">Suchardt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While considerable effort has gone into developing solutions for detecting Personally Identifiable Information (PII) in linguistic data, less research has gone into automating the generation of appropriate pseudonyms and developing evaluation methods, both relevant for the creation of privacy-friendly language resources. We conduct pilot experiments using Masked and Generative Large Language Models to generate predictions for redacted PII-spans in a cloze-like fashion for English legal texts and parallel news articles in Swedish and English. Furthermore, we explore metrics for automatic evaluation of the generated pseudonyms in the legal data, and investigate the effect of part-of-speech constraints on performance. For the parallel, multilingual data, we contribute our manual PII-annotation and conduct a fine-grained error analysis across two of our pseudonym generation methods and a baseline. Our results illustrate the complexity of pseudonym evaluation and the particular challenge of automatic, at-scale evaluation as well as the models’ tendency to predict prototypical and even stereotypical answers.</abstract>
    <identifier type="citekey">szawerna-suchardt-2026-fill</identifier>
    <identifier type="doi">10.63317/42gh3j2hfmca</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.90/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>1155</start>
            <end>1169</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fill-in-the-Blanks: Automatic Generation and Evaluation of Language Models’ Pseudonyms for English and Swedish Texts
%A Szawerna, Maria Irena
%A Suchardt, Jacob Lee
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F szawerna-suchardt-2026-fill
%X While considerable effort has gone into developing solutions for detecting Personally Identifiable Information (PII) in linguistic data, less research has gone into automating the generation of appropriate pseudonyms and developing evaluation methods, both relevant for the creation of privacy-friendly language resources. We conduct pilot experiments using Masked and Generative Large Language Models to generate predictions for redacted PII-spans in a cloze-like fashion for English legal texts and parallel news articles in Swedish and English. Furthermore, we explore metrics for automatic evaluation of the generated pseudonyms in the legal data, and investigate the effect of part-of-speech constraints on performance. For the parallel, multilingual data, we contribute our manual PII-annotation and conduct a fine-grained error analysis across two of our pseudonym generation methods and a baseline. Our results illustrate the complexity of pseudonym evaluation and the particular challenge of automatic, at-scale evaluation as well as the models’ tendency to predict prototypical and even stereotypical answers.
%R 10.63317/42gh3j2hfmca
%U https://aclanthology.org/2026.lrec-1.90/
%U https://doi.org/10.63317/42gh3j2hfmca
%P 1155-1169

Markdown (Informal)

[Fill-in-the-Blanks: Automatic Generation and Evaluation of Language Models’ Pseudonyms for English and Swedish Texts](https://aclanthology.org/2026.lrec-1.90/) (Szawerna & Suchardt, LREC 2026)

• Fill-in-the-Blanks: Automatic Generation and Evaluation of Language Models’ Pseudonyms for English and Swedish Texts (Szawerna & Suchardt, LREC 2026)

ACL

• Maria Irena Szawerna and Jacob Lee Suchardt. 2026. Fill-in-the-Blanks: Automatic Generation and Evaluation of Language Models’ Pseudonyms for English and Swedish Texts. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1155–1169, Palma de Mallorca, Spain. ELRA Language Resource Association.