Papers by Jaroslav Kopčan
Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection (2026.eacl-long)
Copied to clipboard
Ivan Vykopal, Antonia Karamolegkou, Jaroslav Kopčan, Qiwei Peng, Tomáš Javůrek, Michal Gregor, Marian Simko
| Challenge: | Recent advances in multilingual Large Language Models have enabled powerful capabilities for cross-lingual fact-checking. |
| Approach: | They evaluate six open-source multilingual LLMs across 20 languages using a fully multilingual prompting strategy. |
| Outcome: | The proposed model performs better on high-resource languages than on low-resourced ones. |
o-MEGA: Optimized Methods for Explanation Generation and Analysis (2025.emnlp-demos)
Copied to clipboard
| Challenge: | a growing number of transformer-based language models have created challenges for model transparency and trustworthiness. |
| Approach: | They propose a tool to automatically identify the most effective explainable AI methods . they evaluate o-mega on a post-claim matching pipeline using a curated dataset . |
| Outcome: | The proposed tool shows that the most effective explainable AI methods can be implemented in semantic matching tasks. |