{"id":6279,"date":"2026-07-15T10:59:10","date_gmt":"2026-07-15T10:59:10","guid":{"rendered":"https:\/\/ceo.com.pl\/en\/?p=6279"},"modified":"2026-07-15T10:59:10","modified_gmt":"2026-07-15T10:59:10","slug":"poldense-1b-tops-polish-information-retrieval-benchmark-15867","status":"publish","type":"post","link":"https:\/\/ceo.com.pl\/en\/poldense-1b-tops-polish-information-retrieval-benchmark-15867\/","title":{"rendered":"PolDense 1B Tops Polish Information Retrieval Benchmark"},"content":{"rendered":"<p>The AI Lab at Poland\u2019s National Information Processing Institute (OPI) has developed PolDense, a new family of language models designed specifically for information retrieval. It is the latest solution created by the OPI research team as part of its efforts to develop advanced artificial intelligence technologies tailored to the Polish language and the needs of domestic users and institutions.<\/p>\n<p>PolDense models have been designed for systems that process large volumes of unstructured data, particularly search engines, chatbots, AI assistants and applications using the increasingly popular Retrieval-Augmented Generation, or RAG, architecture.<\/p>\n<p>The quality of the PolDense models is reflected in their performance in the Polish Information Retrieval Benchmark (PIRB), one of the most important benchmarks for evaluating the effectiveness of Polish-language information retrieval models. PolDense 1B currently ranks first in the public PIRB ranking, achieving the highest average score among all models evaluated.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_85 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/ceo.com.pl\/en\/poldense-1b-tops-polish-information-retrieval-benchmark-15867\/#AI_Lab_Develops_Key_Components_of_Modern_AI_Systems\" >AI Lab Develops Key Components of Modern AI Systems<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/ceo.com.pl\/en\/poldense-1b-tops-polish-information-retrieval-benchmark-15867\/#OPI_Model_Takes_the_Top_Position_in_the_PIRB_Ranking\" >OPI Model Takes the Top Position in the PIRB Ranking<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/ceo.com.pl\/en\/poldense-1b-tops-polish-information-retrieval-benchmark-15867\/#Six_OPI_Models_Designed_for_Different_Applications\" >Six OPI Models Designed for Different Applications<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/ceo.com.pl\/en\/poldense-1b-tops-polish-information-retrieval-benchmark-15867\/#Open_OPI_Solutions_for_Research_Public_Administration_and_Business\" >Open OPI Solutions for Research, Public Administration and Business<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/ceo.com.pl\/en\/poldense-1b-tops-polish-information-retrieval-benchmark-15867\/#PolDense_Models_Developed_Under_the_LLMs4EU_Project\" >PolDense Models Developed Under the LLMs4EU Project<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"AI_Lab_Develops_Key_Components_of_Modern_AI_Systems\"><\/span>AI Lab Develops Key Components of Modern AI Systems<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>A growing number of solutions based on large language models use the RAG approach, which allows them to generate answers not only from the knowledge stored within the model, but primarily from up-to-date documents retrieved in real time and relevant to a particular domain or industry.<\/p>\n<p>The effectiveness of such systems depends largely on the quality of their information retrieval mechanisms. The best results in this field are currently achieved by so-called dense retrievers. These models use deep neural networks to transform queries and documents into compact vector representations, allowing content to be retrieved based on its meaning rather than solely on keyword matching.<\/p>\n<p>This is precisely the type of information retrieval technology currently being developed by the OPI AI Lab. The team is building the PolDense model family for the Polish language, while also working on EuroDense, a model that will support the most widely used European languages.<\/p>\n<p>\u201cThe release of the PolDense models is another step towards building Poland\u2019s expertise in artificial intelligence. We are creating open technologies that can be used by researchers, public authorities and businesses to develop modern, efficient and secure AI tools. It is worth emphasising that one of OPI\u2019s new models ranks first in the Polish Information Retrieval Benchmark, outperforming multilingual models such as Llama and BGE,\u201d said Jaros\u0142aw Protasiewicz, Director of the National Information Processing Institute.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"OPI_Model_Takes_the_Top_Position_in_the_PIRB_Ranking\"><\/span>OPI Model Takes the Top Position in the PIRB Ranking<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The performance of the PolDense models in the Polish Information Retrieval Benchmark confirms their high quality. PIRB is one of the most important benchmarks used to evaluate the effectiveness of information retrieval models for the Polish language.<\/p>\n<p>PolDense 1B currently occupies first place in the PIRB ranking, recording the highest average score among all evaluated models. It outperforms significantly larger multilingual solutions, including models with nearly 10 billion parameters.<\/p>\n<p>The result confirms that the solutions developed by the OPI AI Lab are among the world\u2019s leading information retrieval technologies for the Polish language. At the same time, they offer a more attractive balance between performance and implementation costs.<\/p>\n<p>\u201cPolDense 1B\u2019s first-place position in the PIRB ranking demonstrates that specialised models designed for the Polish language can set quality standards not only among domestic models, but can also compete effectively with international and multilingual models many times their size. This achievement is the result of many years of research conducted by the OPI AI Lab into modern neural representation models and specialised information retrieval models for Polish,\u201d said S\u0142awomir Dadas, Deputy Head of the AI Lab at OPI.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Six_OPI_Models_Designed_for_Different_Applications\"><\/span>Six OPI Models Designed for Different Applications<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The PolDense family consists of six models based on the ModernBERT architecture and ettin-encoders technology. They range from 17 million to 1 billion parameters, allowing users to select a model suitable both for deployments requiring the highest possible quality and for environments with limited computing resources.<\/p>\n<p>The models can analyse texts of up to 8,192 tokens, enabling them to retain the context of longer documents more effectively and identify the most relevant information with greater accuracy.<\/p>\n<p>The largest model in the family, PolDense 1B, scored 64.11 points in the PIRB benchmark, establishing a new performance level for Polish-language information retrieval. It also outperformed significantly larger multilingual models, including Llama-Embed-Nemotron-8B, which scored 63.73 points, and BGE-Multilingual-Gemma2-9B, which achieved 63.26 points.<\/p>\n<p>The models with 400 million and 150 million parameters offer highly competitive results compared with solutions containing several billion parameters. The smallest variants, with 68 million, 32 million and 17 million parameters, have been designed for deployment on CPUs, mobile devices and edge computing environments.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Open_OPI_Solutions_for_Research_Public_Administration_and_Business\"><\/span>Open OPI Solutions for Research, Public Administration and Business<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The National Information Processing Institute has released the PolDense models as open-source solutions. They can therefore be used to develop custom search mechanisms, RAG systems and tools supporting work with document databases.<\/p>\n<p>PolDense models can not only improve the quality of information retrieval but also reduce implementation costs. Organisations can use smaller and more computationally efficient models without sacrificing a high level of performance.<\/p>\n<p>\u201cPolDense shows that it is possible to develop specialised Polish-language models that not only compete with the world\u2019s largest solutions but also outperform them in many specific tasks. Our objective was to create a family of models suitable for a wide range of applications, from large corporate systems to lightweight solutions operating locally. We are making all the models available free of charge on Hugging Face to support the development of Poland\u2019s AI ecosystem,\u201d said Marek Koz\u0142owski, Head of the AI Lab at the National Information Processing Institute.<\/p>\n<p>\u201cWe are delighted with the success of the PolDense models, but we are not resting on our laurels. In the coming months, the OPI AI Lab plans to release EuroDense, which will support information retrieval in nine European languages,\u201d Koz\u0142owski added.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"PolDense_Models_Developed_Under_the_LLMs4EU_Project\"><\/span>PolDense Models Developed Under the LLMs4EU Project<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The PolDense models were developed as part of the Large Language Models for the European Union project, known as LLMs4EU, which is being implemented by the Alliance for Language Technologies European Digital Infrastructure Consortium, or ALT-EDIC.<\/p>\n<p>The project aims to develop and provide artificial intelligence models, tools and services for five key sectors: research, public services, tourism, telecommunications and energy.<\/p>\n<p>It is also intended to encourage public institutions and small and medium-sized enterprises to adopt European AI technologies. LLMs4EU is co-financed by the European Union under the Digital Europe Programme and by Poland\u2019s Ministry of Digital Affairs.<\/p>\n<p>The PolDense models are available free of charge on the Hugging Face platform.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The AI Lab at Poland\u2019s National Information Processing Institute (OPI) has developed PolDense, a new family of language models designed specifically for information retrieval. It is the latest solution created by the OPI research team as part of its efforts to develop advanced artificial intelligence technologies tailored to the Polish language and the needs of [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":6280,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11],"tags":[2974,2839,47,4741,4742,2732],"class_list":["post-6279","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-artificial-intelligence","tag-content","tag-european-union","tag-jaroslaw-protasiewicz","tag-marek-kozlowski","tag-ranking"],"jetpack_publicize_connections":[],"_links":{"self":[{"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/posts\/6279","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/comments?post=6279"}],"version-history":[{"count":1,"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/posts\/6279\/revisions"}],"predecessor-version":[{"id":6282,"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/posts\/6279\/revisions\/6282"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/media\/6280"}],"wp:attachment":[{"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/media?parent=6279"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/categories?post=6279"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ceo.com.pl\/en\/wp-json\/wp\/v2\/tags?post=6279"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}