@inproceedings{bartanowicz-jassem-2026-evaluation,
title = "Evaluation of Two Leading {P}olish Language Models in a Real-world {RAG} Scenario",
author = "Bartanowicz, Szymon and
Jassem, Krzysztof",
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-1.211/",
doi = "10.63317/36igcwtic7tn",
pages = "2698--2704",
abstract = "This paper presents a comparative evaluation of two leading Polish instruction-tuned language models, Bielik-11B-v2.3-Instruct and PLLuM-12B-nc-chat, within a real-world Retrieval-Augmented Generation (RAG) system designed for the technical documentation of a low-code platform. The study aims to identify the optimal configuration of retrieval and generation components for Polish-language applications. The evaluation was conducted in two stages. First, several embedding models and retrieval methods were tested using standard information retrieval metrics, including NDCG. The OrlikB/KartonBERT-USE-base-v1 model combined with vector-based retrieval achieved the highest performance and was adopted for the second stage. In the generation phase, both models were evaluated using quantitative scoring and pairwise A/B testing with multiple evaluators to ensure robustness. Results show that Bielik-11B-v2.3-Instruct consistently outperformed PLLuM-12B-nc-chat in producing accurate and contextually relevant answers. The study highlights the importance of constructing a reliable golden set, employing a two-phase evaluation pipeline, and selecting appropriate metrics to ensure objective and reproducible assessment of RAG systems in real-world Polish-language contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bartanowicz-jassem-2026-evaluation">
<titleInfo>
<title>Evaluation of Two Leading Polish Language Models in a Real-world RAG Scenario</title>
</titleInfo>
<name type="personal">
<namePart type="given">Szymon</namePart>
<namePart type="family">Bartanowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Jassem</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>This paper presents a comparative evaluation of two leading Polish instruction-tuned language models, Bielik-11B-v2.3-Instruct and PLLuM-12B-nc-chat, within a real-world Retrieval-Augmented Generation (RAG) system designed for the technical documentation of a low-code platform. The study aims to identify the optimal configuration of retrieval and generation components for Polish-language applications. The evaluation was conducted in two stages. First, several embedding models and retrieval methods were tested using standard information retrieval metrics, including NDCG. The OrlikB/KartonBERT-USE-base-v1 model combined with vector-based retrieval achieved the highest performance and was adopted for the second stage. In the generation phase, both models were evaluated using quantitative scoring and pairwise A/B testing with multiple evaluators to ensure robustness. Results show that Bielik-11B-v2.3-Instruct consistently outperformed PLLuM-12B-nc-chat in producing accurate and contextually relevant answers. The study highlights the importance of constructing a reliable golden set, employing a two-phase evaluation pipeline, and selecting appropriate metrics to ensure objective and reproducible assessment of RAG systems in real-world Polish-language contexts.</abstract>
<identifier type="citekey">bartanowicz-jassem-2026-evaluation</identifier>
<identifier type="doi">10.63317/36igcwtic7tn</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.211/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2698</start>
<end>2704</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation of Two Leading Polish Language Models in a Real-world RAG Scenario
%A Bartanowicz, Szymon
%A Jassem, Krzysztof
%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 bartanowicz-jassem-2026-evaluation
%X This paper presents a comparative evaluation of two leading Polish instruction-tuned language models, Bielik-11B-v2.3-Instruct and PLLuM-12B-nc-chat, within a real-world Retrieval-Augmented Generation (RAG) system designed for the technical documentation of a low-code platform. The study aims to identify the optimal configuration of retrieval and generation components for Polish-language applications. The evaluation was conducted in two stages. First, several embedding models and retrieval methods were tested using standard information retrieval metrics, including NDCG. The OrlikB/KartonBERT-USE-base-v1 model combined with vector-based retrieval achieved the highest performance and was adopted for the second stage. In the generation phase, both models were evaluated using quantitative scoring and pairwise A/B testing with multiple evaluators to ensure robustness. Results show that Bielik-11B-v2.3-Instruct consistently outperformed PLLuM-12B-nc-chat in producing accurate and contextually relevant answers. The study highlights the importance of constructing a reliable golden set, employing a two-phase evaluation pipeline, and selecting appropriate metrics to ensure objective and reproducible assessment of RAG systems in real-world Polish-language contexts.
%R 10.63317/36igcwtic7tn
%U https://aclanthology.org/2026.lrec-1.211/
%U https://doi.org/10.63317/36igcwtic7tn
%P 2698-2704
Markdown (Informal)
[Evaluation of Two Leading Polish Language Models in a Real-world RAG Scenario](https://aclanthology.org/2026.lrec-1.211/) (Bartanowicz & Jassem, LREC 2026)
ACL