Ján Cegin

According to our database, Ján Cegin authored at least 9 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification.

Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky

CoRR, 2024

LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?

Ján Cegin, Jakub Simko, Peter Brusilovsky

CoRR, 2024

Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation.

Branislav Pecher, Ján Cegin, Róbert Belanec, Jakub Simko, Ivan Srba, Mária Bieliková

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation.

Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness.

Ján Cegin, Jakub Simko, Peter Brusilovsky

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

2022

A Game for Crowdsourcing Adversarial Examples for False Information Detection.

Ján Cegin, Jakub Simko, Peter Brusilovsky

Proceedings of the 2nd Workshop on Adverse Impacts and Collateral Effects of Artificial Intelligence Technologies, 2022

2020

Machine learning based test data generation for safety-critical software.

Ján Cegin

Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Synthesized dataset for search-based test data generation methods focused on MC/DC criterion.

Ján Cegin, Karol Rástocný, Mária Bieliková

Proceedings of the 20th IEEE International Conference on Software Quality, 2020

Test Data Generation for MC/DC Criterion using Reinforcement Learning.

Ján Cegin, Karol Rástocný

Proceedings of the 13th IEEE International Conference on Software Testing, 2020