@inproceedings{poh-etal-2026-multilingual,
title = "The Multilingual Euphemism Benchmark: Datasets and Baselines for Pragmatic Language Understanding",
author = "Poh, Whitney and
Sammartino, Julia and
Andrew, Jasper and
Kiera{\'s}, Witold and
Zawadzka-Paluektau, Natalia and
Dilai, Iryna and
Barak, Libby and
Peng, JIng and
Feldman, Anna",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.579/",
doi = "10.63317/5im6zovfyg3t",
pages = "7307--7319",
abstract = "Euphemisms are words or phrases used to soften or indirectly refer to taboo or sensitive topics. They pose interpretation challenges because the same expression may appear in different senses depending on context: literal, figurative but non-euphemistic, or euphemistic. For example, pull the plug may refer euphemistically to ending a patient{'}s life support, figuratively to canceling a project or funding, or literally to unplugging a device. Euphemisms also vary across languages and cultures in both their surface forms and the contexts in which they are conventionally used. Previous work introduced datasets for the computational study of euphemisms in five languages. We extend this line of work by introducing two new annotated datasets for euphemism detection in Polish and Ukrainian and by standardizing resources for all seven languages into a unified benchmark format that supports cross-lingual evaluation. Finally, we provide zero-shot and few-shot baselines using GPT-5-nano. We ran each configuration five times and report the average score, establishing reference scores for multilingual pragmatic understanding. In addition, we performed pilot tests using Qwen3-4B on the English and Chinese datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poh-etal-2026-multilingual">
<titleInfo>
<title>The Multilingual Euphemism Benchmark: Datasets and Baselines for Pragmatic Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Whitney</namePart>
<namePart type="family">Poh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Sammartino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jasper</namePart>
<namePart type="family">Andrew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Witold</namePart>
<namePart type="family">Kieraś</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Zawadzka-Paluektau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Dilai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Barak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JIng</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</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>Euphemisms are words or phrases used to soften or indirectly refer to taboo or sensitive topics. They pose interpretation challenges because the same expression may appear in different senses depending on context: literal, figurative but non-euphemistic, or euphemistic. For example, pull the plug may refer euphemistically to ending a patient’s life support, figuratively to canceling a project or funding, or literally to unplugging a device. Euphemisms also vary across languages and cultures in both their surface forms and the contexts in which they are conventionally used. Previous work introduced datasets for the computational study of euphemisms in five languages. We extend this line of work by introducing two new annotated datasets for euphemism detection in Polish and Ukrainian and by standardizing resources for all seven languages into a unified benchmark format that supports cross-lingual evaluation. Finally, we provide zero-shot and few-shot baselines using GPT-5-nano. We ran each configuration five times and report the average score, establishing reference scores for multilingual pragmatic understanding. In addition, we performed pilot tests using Qwen3-4B on the English and Chinese datasets.</abstract>
<identifier type="citekey">poh-etal-2026-multilingual</identifier>
<identifier type="doi">10.63317/5im6zovfyg3t</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.579/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7307</start>
<end>7319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Multilingual Euphemism Benchmark: Datasets and Baselines for Pragmatic Language Understanding
%A Poh, Whitney
%A Sammartino, Julia
%A Andrew, Jasper
%A Kieraś, Witold
%A Zawadzka-Paluektau, Natalia
%A Dilai, Iryna
%A Barak, Libby
%A Peng, JIng
%A Feldman, Anna
%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 poh-etal-2026-multilingual
%X Euphemisms are words or phrases used to soften or indirectly refer to taboo or sensitive topics. They pose interpretation challenges because the same expression may appear in different senses depending on context: literal, figurative but non-euphemistic, or euphemistic. For example, pull the plug may refer euphemistically to ending a patient’s life support, figuratively to canceling a project or funding, or literally to unplugging a device. Euphemisms also vary across languages and cultures in both their surface forms and the contexts in which they are conventionally used. Previous work introduced datasets for the computational study of euphemisms in five languages. We extend this line of work by introducing two new annotated datasets for euphemism detection in Polish and Ukrainian and by standardizing resources for all seven languages into a unified benchmark format that supports cross-lingual evaluation. Finally, we provide zero-shot and few-shot baselines using GPT-5-nano. We ran each configuration five times and report the average score, establishing reference scores for multilingual pragmatic understanding. In addition, we performed pilot tests using Qwen3-4B on the English and Chinese datasets.
%R 10.63317/5im6zovfyg3t
%U https://aclanthology.org/2026.lrec-1.579/
%U https://doi.org/10.63317/5im6zovfyg3t
%P 7307-7319
Markdown (Informal)
[The Multilingual Euphemism Benchmark: Datasets and Baselines for Pragmatic Language Understanding](https://aclanthology.org/2026.lrec-1.579/) (Poh et al., LREC 2026)
ACL
- Whitney Poh, Julia Sammartino, Jasper Andrew, Witold Kieraś, Natalia Zawadzka-Paluektau, Iryna Dilai, Libby Barak, JIng Peng, and Anna Feldman. 2026. The Multilingual Euphemism Benchmark: Datasets and Baselines for Pragmatic Language Understanding. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 7307–7319, Palma de Mallorca, Spain. ELRA Language Resource Association.