Automated Knowledge Base Construction Using Large Language Models

An open-access paper entitled “Pre-training Aware Directed Reasoning for Closed-Book Knowledge Base Construction” by Mikołaj Tym, a member of our Department, has been published. The paper introduces a method that uses large language models to automatically complete knowledge bases. The research was presented at a workshop held as part of the international EMNLP 2026 conference, which took place in Budapest, Hungary, from October 24 to 29, 2026.

Can Large Language Models Replace Human Annotators? Research by Our Team Presented at EMNLP 2026

The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026) took place in Budapest, Hungary, from 24 to 29 October 2026. It is one of the leading international research conferences in the field of natural language processing (NLP). During the conference, Dr. Milena Stróżyna presented the paper entitled “Multi-Model Framework for Sentiment Annotation: A Use Case of Multilingual Wikipedia”. The study introduces an approach in which multiple artificial … Read More

Our Researchers Among the Finalists of the Pyrkon 2027 Competition

Dr. Włodzimierz Lewoniewski and Izabela Czumałowska have been selected as finalists in the 6th edition of the competition to become a speaker at Pyrkon’s Scientific Zone. Winning the competition will give them the opportunity to deliver their own presentation at Pyrkon 2027, one of Europe’s largest fantasy and science fiction festivals.

SRG Data Science: Inaugural Meeting 2026/2027

On 22 October 2026, SRG Data Science held its inaugural meeting, during which the student research group’s plans and key priorities for the 2026/2027 academic year were presented. Over the coming months, the research group will focus on developing practical skills in data analysis, Python programming and artificial intelligence.

BIS 2027 will be held in Poznań

The 27th edition of the international BIS conference will take place on 23-25 June 2027 at Poznań University of Economics and Business, Poland. BIS is a well-established international conference dedicated to business information systems. Since its inception, it has served as a forum for researchers and industry practitioners to exchange knowledge and share the latest research on the development, implementation, use, and improvement of information systems supporting business operations.

Measuring Wikipedia Quality at Scale: Assessment of Content, Information Sources, Data Visualizations

At the international conference “Open Knowledge: Wikimedia & Research in the CEE Region”, held on October 9–10, 2026, in Katowice, Dr. Włodzimierz Lewoniewski delivered a talk entitled “Measuring Wikipedia Quality at Scale: Assessment of Content, Information Sources, Data Visualizations”. The presentation focused on the use of artificial intelligence and advanced data analysis methods to automatically assess the quality of information on Wikipedia.

13th International Scientific Conference “Knowledge and Information Technologies in Creating Entrepreneurship”

On October 8–9, 2026, the 13th International Scientific Conference “Knowledge and Information Technologies in Creating Entrepreneurship” took place in Olsztyn near Częstochowa, Poland. The annual event brought together researchers in the field of business informatics. This year’s discussions focused on digital transformation and artificial intelligence.

ACL 2026: Success in an International Narrative Similarity Competition

A system developed by our researcher secured second place in the international SemEval-2026 competition focused on narrative similarity. Its developer, Marcin Sawiński, presented his research at ACL 2026 in San Diego, United States, one of the world’s leading international conferences on natural language processing.

How Can AI Avoid Averaging Out Emotions? A New Sentiment Analysis Method Combining Language Models and Graph Neural Networks

At the ACL 2026 conference in San Diego, USA, researchers from our Department presented their paper entitled “PUEB-DimASR at SemEval-2026 Task 3: Escaping the Mean Regression Trap with Graph-Enhanced Transformers for Dimensional Aspect-Based Sentiment Regression“, prepared as part of the SemEval-2026 workshop. The paper was authored by Oskar Riewe-Perła and Prof. Agata Filipowska.

Reducing the Influence of Content on Syllogistic Reasoning in Large Language Models

During the international ACL 2026 conference in San Diego, USA, Ewelina Księżniak presented research findings on reducing content bias in syllogistic reasoning by large language models. Her poster was based on the paper entitled “Team ewelinaksiez at SemEval-2026 Task 11: Reducing Content Bias in Syllogistic Reasoning via Semantic Abstraction”.