@inproceedings{seweryn-etal-2025-pllum,
title = "{PLL}u{M}-Align: {P}olish Preference Dataset for Large Language Model Alignment",
author = "Seweryn, Karolina and
Ko{\l}os, Anna and
Karli{\'n}ska, Agnieszka and
Lorenc, Katarzyna and
Dziewulska, Katarzyna and
Chrabaszcz, Maciej and
Krasnodebska, Aleksandra and
Betscher, Paula and
Cie{\'s}li{\'n}ska, Zofia and
Kowol, Katarzyna and
Moska, Julia and
Motyka, Dawid and
Walkowiak, Pawe{\l} and
{\.Z}uk, Bartosz and
Janz, Arkadiusz",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1219/",
pages = "23890--23919",
ISBN = "979-8-89176-332-6",
abstract = "Alignment is the critical process of minimizing harmful outputs by teaching large language models (LLMs) to prefer safe, helpful and appropriate responses. While the majority of alignment research and datasets remain overwhelmingly English-centric, ensuring safety across diverse linguistic and cultural contexts requires localized resources. In this paper, we introduce the first Polish preference dataset PLLuM-Align, created entirely through human annotation to reflect Polish language and cultural nuances. The dataset includes response rating, ranking, and multi-turn dialog data. Designed to reflect the linguistic subtleties and cultural norms of Polish, this resource lays the groundwork for more aligned Polish LLMs and contributes to the broader goal of multilingual alignment in underrepresented languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seweryn-etal-2025-pllum">
<titleInfo>
<title>PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karolina</namePart>
<namePart type="family">Seweryn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kołos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Karlińska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarzyna</namePart>
<namePart type="family">Lorenc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarzyna</namePart>
<namePart type="family">Dziewulska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Chrabaszcz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Krasnodebska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Betscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zofia</namePart>
<namePart type="family">Cieślińska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarzyna</namePart>
<namePart type="family">Kowol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Moska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawid</namePart>
<namePart type="family">Motyka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Walkowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bartosz</namePart>
<namePart type="family">Żuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkadiusz</namePart>
<namePart type="family">Janz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Alignment is the critical process of minimizing harmful outputs by teaching large language models (LLMs) to prefer safe, helpful and appropriate responses. While the majority of alignment research and datasets remain overwhelmingly English-centric, ensuring safety across diverse linguistic and cultural contexts requires localized resources. In this paper, we introduce the first Polish preference dataset PLLuM-Align, created entirely through human annotation to reflect Polish language and cultural nuances. The dataset includes response rating, ranking, and multi-turn dialog data. Designed to reflect the linguistic subtleties and cultural norms of Polish, this resource lays the groundwork for more aligned Polish LLMs and contributes to the broader goal of multilingual alignment in underrepresented languages.</abstract>
<identifier type="citekey">seweryn-etal-2025-pllum</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1219/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>23890</start>
<end>23919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment
%A Seweryn, Karolina
%A Kołos, Anna
%A Karlińska, Agnieszka
%A Lorenc, Katarzyna
%A Dziewulska, Katarzyna
%A Chrabaszcz, Maciej
%A Krasnodebska, Aleksandra
%A Betscher, Paula
%A Cieślińska, Zofia
%A Kowol, Katarzyna
%A Moska, Julia
%A Motyka, Dawid
%A Walkowiak, Paweł
%A Żuk, Bartosz
%A Janz, Arkadiusz
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F seweryn-etal-2025-pllum
%X Alignment is the critical process of minimizing harmful outputs by teaching large language models (LLMs) to prefer safe, helpful and appropriate responses. While the majority of alignment research and datasets remain overwhelmingly English-centric, ensuring safety across diverse linguistic and cultural contexts requires localized resources. In this paper, we introduce the first Polish preference dataset PLLuM-Align, created entirely through human annotation to reflect Polish language and cultural nuances. The dataset includes response rating, ranking, and multi-turn dialog data. Designed to reflect the linguistic subtleties and cultural norms of Polish, this resource lays the groundwork for more aligned Polish LLMs and contributes to the broader goal of multilingual alignment in underrepresented languages.
%U https://aclanthology.org/2025.emnlp-main.1219/
%P 23890-23919
Markdown (Informal)
[PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment](https://aclanthology.org/2025.emnlp-main.1219/) (Seweryn et al., EMNLP 2025)
ACL
- Karolina Seweryn, Anna Kołos, Agnieszka Karlińska, Katarzyna Lorenc, Katarzyna Dziewulska, Maciej Chrabaszcz, Aleksandra Krasnodebska, Paula Betscher, Zofia Cieślińska, Katarzyna Kowol, Julia Moska, Dawid Motyka, Paweł Walkowiak, Bartosz Żuk, and Arkadiusz Janz. 2025. PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 23890–23919, Suzhou, China. Association for Computational Linguistics.