PLLuM is a family of large language models (LLMs) specialized in Polish with additional English data incorporated for broader generalization. Developed through an extensive collaboration with various data providers, PLLuM models are built on high-quality text corpora and refined through instruction tuning, preference learning, and advanced alignment techniques. These models are intended to generate contextually coherent text, offer assistance in various tasks (e.g., question answering, summarization), and serve as a foundation for specialized applications such as domain-specific intelligent assistants.
In 2024, PLLuM models were developed by the PLLuM consortium. Since 2025, their development has continued under HIVE AI, a broader alliance of research institutions and organizations delivering digital public services, focused on open language technologies for Polish public administration.
Key Highlights
Extensive Data Collection
We gathered large-scale, high-quality text data in Polish and English, focusing on rigorous cleaning and deduplication to ensure the highest training standards.
Organic Instruction Dataset
We curated the largest Polish collection of manually created “organic instructions”. This human-authored instruction set is based on an extensive typology of human-model interactions and it covers a range of subtle aspects of supervised fine-tuning (SFT) that might be overlooked with automated approaches (including large scale distillation of 'strong LLMs'). It was also designed to mitigate negative linguistic transfer from non-Polish textual data used in the pre-training phase.
Polish Preference Corpus
We created and expanded the first Polish-language preference corpus, featuring prompts and multiple model responses manually assessed by a demographically diverse team of annotators. This dataset teaches the model not only correctness (factual and linguistic) but also balance and safety—especially for potentially controversial or adversarial topics.
Evaluation Benchmarks
We developed custom benchmarks to evaluate our models on tasks relevant to Polish public administration, where PLLuM achieved top scores among all tested models. In broader Polish-language tasks, PLLuM models also attain state-of-the-art results.
Model Description
Below is a summary of the new PLLuM (denoted as 2512) models, created in December 2025. All model names link to their respective Hugging Face resources, while the base models and licenses link to the relevant source models or license references. The model with the -chat suffix has been aligned to human preferences and is generally safer and more efficient for use in dialogue and general-purpose scenarios.
Pretraining: Models were continued-pretrained on large-scale Polish corpora combined with a range of English texts. Following rigorous cleaning and deduplication, the dataset comprised ~6.7B whitespace.
Instruction Fine-Tuning: We fine-tuned the models using approximately 70k manually curated Polish "organic instructions," 33k programmatically derived instructions from high-quality Polish corpora, 15k RAG-style context-processing instructions, and 45k synthetic, context-aware instructions generated by high-performing, permissively licensed LLMs such as Mixtral8x22 and Deepseek V3.
Alignment and Preference Learning: Using ~60k manually annotated preference pairs, we taught the models to produce safer, balanced, and contextually appropriate responses, even in adversarial or sensitive cases.
Intended Use Cases
General Language Tasks: Text generation, summarization, extraction, question answering, etc.
Domain-Specific Assistants: Especially effective for Polish public administration and legal or bureaucratic topics where domain-aware retrieval is required.
Research & Development: Building blocks for downstream AI applications in academic or industrial settings, where a strong command of the Polish language is essential.
How to Use
Each PLLuM model can be loaded via the Hugging Face Transformers library (or compatible frameworks). For RAG-based scenarios, pair the model with a relevant vector store or document retrieval system.
Below are some recommended steps and code snippets:
1. Installation
Make sure you have the latest versions of transformers and torch (or another compatible deep learning framework) installed:
bash
12pip install transformers accelerate torch
2. Using Transformers (AutoModelForCausalLM)
This is the recommended way for fine-grained control over generation parameters.
Your results may vary depending on model parameters (e.g., temperature, top_k, top_p), hardware, and other settings.
4. Retrieval Augmented Generation (RAG)
During post-training, the models were additionally trained to perform well in Retrieval-Augmented Generation (RAG) settings. The prompt is in .jinja format, where docs is a list of document texts and question is a query that should be answered based on the provided documents. If there is no answer in the provided documents model generates "Nie udało mi się odnaleźć odpowiedzi na pytanie".
Prompt:
Numerowana lista dokumentów jest poniżej:
---------------------
<results>{% for doc in docs %}
Dokument: {{ loop.index0 }}
{{ doc }}
{% endfor %}</results>
---------------------
Odpowiedz na pytanie użytkownika wykorzystując tylko informacje znajdujące się w dokumentach, a nie wcześniejszą wiedzę.
Udziel wysokiej jakości, poprawnej gramatycznie odpowiedzi w języku polskim. Odpowiedź powinna zawierać cytowania do dokumentów, z których pochodzą informacje. Zacytuj dokument za pomocą symbolu [nr_dokumentu] powołując się na fragment np. [0] dla fragmentu z dokumentu 0. Jeżeli w dokumentach nie ma informacji potrzebnych do odpowiedzi na pytanie, zamiast odpowiedzi zwróć tekst: "Nie udało mi się odnaleźć odpowiedzi na pytanie".
Pytanie: {{ question }}
Training Procedure
hyperparameters: Vary based on model size, typically including Adam or AdamW optimizers, a range of batch sizes, and carefully tuned learning rates.
Hardware & Duration: Training using Bem2 (up to 300xH100 GPUs) and Helios HPCs.
Evaluation and Benchmarks
Public Administration: PLLuM models demonstrated top-tier performance in specialized tasks relevant to government services.
Polish Language Tasks: Across a variety of internal benchmarks and standard corpora, PLLuM consistently outperforms other models in accuracy, coherence, and safety metrics.
Custom Tests: A unique preference corpus and alignment tests ensure robust, safe, and contextually accurate responses.
Limitations and Bias
Potential Hallucinations: Like other LLMs, PLLuM may occasionally produce factually incorrect or fabricated content.
Sensitivity & Bias: While extensive preference learning has been done, biases might still emerge, especially in controversial or subjective topics.
Context Length: Very long context tasks may challenge certain models, depending on memory constraints.
Ethical Considerations
PLLuM models are designed for constructive and responsible usage. Users should exercise caution when deploying them in production scenarios, especially for sensitive or regulated domains. Despite efforts to minimize harmful outputs, there is always a risk of generating offensive, biased, or inappropriate text. Human oversight and due diligence are advised.
If you use PLLuM models or any part of this repository in your research or deployment, please cite as follows (BibTeX):
@article{kocon2025pllum,
title = {PLLuM: A Family of Polish Large Language Models},
author = {Jan Kocoń and Maciej Piasecki and Arkadiusz Janz and Teddy Ferdinan and Łukasz Radliński and Bartłomiej Koptyra and Marcin Oleksy and Stanisław Woźniak and Paweł Walkowiak and Konrad Wojtasik and Julia Moska and Tomasz Naskręt and Bartosz Walkowiak and Mateusz Gniewkowski and Kamil Szyc and Dawid Motyka and Dawid Banach and Jonatan Dalasiński and Ewa Rudnicka and Bartłomiej Alberski and Tomasz Walkowiak and Aleksander Szczęsny and Maciej Markiewicz and Tomasz Bernaś and Hubert Mazur and Kamil Żyta and Mateusz Tykierko and Grzegorz Chodak and Tomasz Kajdanowicz and Przemysław Kazienko and Agnieszka Karlińska and Karolina Seweryn and Anna Kołos and Maciej Chrabąszcz and Katarzyna Lorenc and Aleksandra Krasnodębska and Artur Wilczek and Katarzyna Dziewulska and Paula Betscher and Zofia Cieślińska and Katarzyna Kowol and Daria Mikoś and Maciej Trzciński and Dawid Krutul and Marek Kozłowski and Sławomir Dadas and Rafał Poświata and Michał Perełkiewicz and Małgorzata Grębowiec and Maciej Kazuła and Marcin Białas and Roman Roszko and Danuta Roszko and Jurgita Vaičenonienė and Andrius Utka and Paweł Levchuk and Paweł Kowalski and Irena Prawdzic-Jankowska and Maciej Ogrodniczuk and Monika Borys and Anna Bulińska and Wiktoria Gumienna and Witold Kieraś and Dorota Komosińska and Katarzyna Krasnowska-Kieraś and Łukasz Kobyliński and Martyna Lewandowska and Marek Łaziński and MikoŁaj Łątkowski and Dawid Mastalerz and Beata Milewicz and Agnieszka Anna Mykowiecka and Angelika Peljak-Łapińska and Sandra Penno and Zuzanna Przybysz and Michał Rudolf and Piotr Rybak and Karolina Saputa and Aleksandra Tomaszewska and Aleksander Wawer and Marcin Woliński and Joanna Wołoszyn and Alina Wróblewska and Bartosz Żuk and Filip Żarnecki and Konrad Kaczyński and Anna Cichosz and Zuzanna Deckert and Monika Garnys and Izabela Grabarczyk and Wojciech Janowski and Sylwia Karasińska and Aleksandra Kujawiak and Piotr Misztela and Maria Szymańska and Karolina Walkusz and Igor Siek and Jakub Kwiatkowski and Piotr Pęzik},
year = 2025,
journal = {arXiv preprint arXiv:2511.03823},
url = {https://arxiv.org/abs/2511.03823},
eprint = {2511.03823},
archiveprefix = {arXiv},
primaryclass = {cs.CL}}
As part of the project, datasets described in the following publications were also created:
@inproceedings{seweryn-etal-2025-pllum,
title = "{PLL}u{M}-Align: {P}olish Preference Dataset for Large Language Model Alignment",
author = "Seweryn, Karolina and Kołos, Anna and Karlińska, Agnieszka and Lorenc, Katarzyna and Dziewulska, Katarzyna and Chrabąszcz, Maciej and Krasnodębska, Aleksandra and Betscher, Paula and Cieślińska, Zofia and Kowol, Katarzyna and Moska, Julia and Motyka, Dawid and Walkowiak, Paweł and Żuk, 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/",
doi = "10.18653/v1/2025.emnlp-main.1219",
pages = "23879--23908",
ISBN = "979-8-89176-332-6"}
@article{pkezik2025pllum,
author = {Pezik, Piotr and Kaczyński, Konrad and Cichosz, Anna and Deckert, Zuzanna and Garnys, Monika and Grabarczyk, Izabela and Janowski, Wojciech and Karasińska, Sylwia and Kujawiak, Aleksandra and Misztela, Piotr and Szymańska, Maria and Walkusz, Karolina and Siek, Igor and Chrabaszcz, Maciej and Kołos, Anna and Karlińska, Agnieszka and Seweryn, Karolina and Krasnodębska, Aleksandra and Kocoń, Jan},
year = {2025},
month = {11},
pages = {},
title = {The PLLuM Instruction Corpus},
doi = {10.48550/arXiv.2511.17161}
}
Creators & Consortium
The PLLuM second-generation models are developed under the banner of HIVE AI – a new initiative uniting scientific institutions and digital service providers working together to develop and implement open language technologies for the Polish public sector. HIVE AI continues the mission of the original PLLuM project, expanding it into a coordinated effort to build, improve, and deploy Polish language models in real-world administrative applications.
Contact and Support
For questions or contributions, please reach out via: hive@nask.pl
We welcome feedback, collaboration, and further exploration of PLLuM models!
Acknowledgements
Project financed by the Minister of Digital Affairs under the targeted subsidy No. 1/WII/DBI/2025: “HIVE AI: Development and Pilot Implementation of LLMs in the Polish Public Administration”
Funding Amount: approx. 18.5 mln PLN
Contract Signing Date: 2025-03-25
