Papers by Anna Kołos
PLLuM-Align: Polish Preference Dataset for Large Language Model Alignment (2025.emnlp-main)
Copied to clipboard
Karolina Seweryn, Anna Kołos, Agnieszka Karlińska, Katarzyna Lorenc, Katarzyna Dziewulska, Maciej Chrabaszcz, Aleksandra Krasnodebska, Paula Betscher, Zofia Cieślińska, Katarzyna Kowol, Julia Moska, Dawid Motyka, Paweł Walkowiak, Bartosz Żuk, Arkadiusz Janz
| Challenge: | Large language models generate preferred responses while avoiding harmful or inappropriate outputs, despite their ability to generate cross-language transferability. |
| Approach: | They introduce the first Polish preference dataset PLLuM-Align, created entirely through human annotation to reflect Polish language and cultural nuances. |
| Outcome: | The proposed dataset lays the groundwork for more aligned Polish LLMs and contributes to the broader goal of multilingual alignment in underrepresented languages. |
Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can generate highly persuasive text, raising concerns about misuse for propaganda, manipulation, and other harmful purposes. |
| Approach: | They propose a multilingual benchmark to compare LLM-generated persuasive texts with human-written ones. |
| Outcome: | The proposed benchmark compares human-authored and LLM-generated persuasive texts . it finds that overtly persuasive LLMs are easier to detect than human-written ones . |
Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse (2025.acl-long)
Copied to clipboard
| Challenge: | specialized Polish language models are more effective at detecting harmful content than traditional methods. |
| Approach: | They propose a Polish-language dataset for erotic content detection that captures ambiguity, violence, and socially unacceptable behaviors. |
| Outcome: | The proposed dataset shows that specialized Polish language models achieve superior performance compared to multilingual alternatives, with transformer-based architectures showing particular strength in handling imbalanced categories. |