Papers by Emilia Wiśnios
Wait, that’s not an option: LLMs Robustness with Incorrect Multiple-Choice Options (2025.acl-long)
Copied to clipboard
| Challenge: | Using a framework that combines instruction-following with critical reasoning, we show that the ability of LLMs to override defaults when faced with invalid options is impaired by alignment techniques. |
| Approach: | They propose a framework for evaluating LLMs’ capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. |
| Outcome: | The proposed framework improves models' ability to override defaults when faced with invalid options while minimizing the impact of model size and training techniques on the model. |
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. |