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”.

Artificial Intelligence in Sentiment Analysis of Multilingual Wikipedia: Classifiers vs. Large Language Models

An open-access paper by researchers from our Department entitled “Evaluating Multilingual Sentiment Classifiers Using an LLM-Annotated Wikipedia Benchmark” has been published. Authors of the work: Dr. Milena Stróżyna, Dr. Włodzimierz Lewoniewski, Izabela Czumałowska. The paper was presented at ACL 2026 in San Diego, held from July 2 to 7, 2026.

Presentation at EACL 2026

Between March 24-29, 2026, Ewelina Księżniak participated in EACL 2026 (the 19th Conference of the European Chapter of the Association for Computational Linguistics) – one of the leading European scientific conferences in the field of natural language processing, bringing together researchers working in areas such as computational linguistics, artificial intelligence, and text analysis. This year’s edition of the conference took place in Rabat, Morocco.

Analyzing Wikipedia Neutrality Using Artificial Intelligence

An article by our researchers, titled “Cross-Topic Sentiment Analysis of Wikipedia Articles: A Comparative Study of AI Models“, has been published. The study focuses on one of Wikipedia’s core principles: the neutral point of view (NPOV), which requires information to be presented impartially. The publication demonstrates how modern AI methods can support the analysis of information quality on a global scale, while also revealing the complexity and challenges behind the … Read More

Research trends in blockchain and crypto-assets

A study authored by our researchers, dedicated to the analysis of research trends in the fields of blockchain technology and crypto-assets, has been published in open access on the Elsevier publishing platform. The study analyzes more than 50,000 scientific publications from the years 2015–2025, and its findings provide a unique, data-driven picture of how blockchain research has evolved over time.

Scientific Presentations: From Blockchain Trends to the Quality of Visualizations in Wikipedia

At the KES 2025 international scientific conference, papers authored by our researchers were presented, reporting the results of research on the evolution of scientific trends in blockchain technology and on the quality and distribution of data visualizations in the Polish Wikipedia.

Presentation at the IJCAI 2025 conference

The paper on automatic analysis of Wikipedia content neutrality, authored by our researchers, was presented at IJCAI 2025 (the 34th International Joint Conference on Artificial Intelligence). The event took place on 16-22 August 2025 in Montreal, Canada.

Department of Information Systems at ACL 2025

Employees of the Department of Information Systems took part in ACL 2025 (the 63rd Annual Meeting of the Association for Computational Linguistics), a top-tier conference on artificial intelligence, held in Vienna in the last week of July 2025. Researchers presented results published in the ACL Anthology, prepared as part of a shared task on the detection and classification of persuasion techniques in Slavic languages.

Political Narratives and Misinformation During COVID-19: Insights from an Analysis of Polish Twitter

At the BIS 2025 conference, Ewelina Księżniak presented the results of a research project focused on the analysis of political narratives and misinformation spread via social media during the COVID-19 pandemic. Our researchers investigated how supporters of four Polish political parties – Law and Justice (PiS), Civic Platform (PO), Confederation, The Left (Lewica) – engaged in pandemic-related discussions. The study employed natural language processing techniques, including BERTopic and stance classification … Read More

Are company descriptions on Wikipedia neutral? Sentiment-analysis tools in practice

A new paper by our researchers has been published on the Springer website. It explores the sentiment of Wikipedia articles about companies using a range of artificial-intelligence models. The study set out to determine how well each model copes with assessing the sentiment of Wikipedia’s characteristically long articles, and to examine how that sentiment varies across industries and article-quality classes.