Ján Cegin - RankMe

23 papers A* 2Journal 10Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification. EACL (Findings) Branislav Pecher, Ján Cegin, Róbert Belanec, Ivan Srba, Jakub Simko, Mária Bieliková
2026	J	`jnl`	Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification. CoRR Branislav Pecher, Ján Cegin, Róbert Belanec, Ivan Srba, Jakub Simko, Mária Bieliková
2026	—	`conf`	MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models. EACL (Findings) Martin Hyben, Sebastian Kula, Ján Cegin, Jakub Simko, Ivan Srba, Róbert Móro
2026	J	`jnl`	MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models. CoRR Martin Hyben, Sebastian Kula, Ján Cegin, Jakub Simko, Ivan Srba, Róbert Móro
2026	J	`jnl`	Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification. CoRR Branislav Pecher, Michal Spiegel, Róbert Belanec, Ján Cegin
2026	—	`conf`	RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets. EACL (Volume 1: Long Papers) Ján Cegin, Branislav Pecher, Ivan Srba, Jakub Simko
2025	A*	`conf`	A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages. EMNLP Tatiana Anikina, Ján Cegin, Jakub Simko, Simon Ostermann
2025	J	`jnl`	A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages. CoRR Tatiana Anikina, Ján Cegin, Jakub Simko, Simon Ostermann
2025	—	`conf`	LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? NAACL (Long Papers) Ján Cegin, Jakub Simko, Peter Brusilovsky
2025	J	`jnl`	RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets. CoRR Ján Cegin, Branislav Pecher, Ivan Srba, Jakub Simko
2025	—	`conf`	Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation. EMNLP (Findings) Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky
2024	—	`conf`	Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation. ACL (1) Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky
2024	J	`jnl`	Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation. CoRR Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky
2024	—	`conf`	Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation. EMNLP (Findings) Branislav Pecher, Ján Cegin, Róbert Belanec, Jakub Simko, Ivan Srba, Mária Bieliková
2024	J	`jnl`	Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation. CoRR Branislav Pecher, Ján Cegin, Róbert Belanec, Jakub Simko, Ivan Srba, Mária Bieliková
2024	J	`jnl`	LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? CoRR Ján Cegin, Jakub Simko, Peter Brusilovsky
2024	J	`jnl`	Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification. CoRR Ján Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Mária Bieliková, Peter Brusilovsky
2023	A*	`conf`	ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness. EMNLP Ján Cegin, Jakub Simko, Peter Brusilovsky
2023	J	`jnl`	ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness. CoRR Ján Cegin, Jakub Simko, Peter Brusilovsky
2022	—	`conf`	A Game for Crowdsourcing Adversarial Examples for False Information Detection. AiOfAi@IJCAI Ján Cegin, Jakub Simko, Peter Brusilovsky
2020	—	`conf`	Machine learning based test data generation for safety-critical software. ESEC/SIGSOFT FSE Ján Cegin
2020	—	`conf`	Synthesized dataset for search-based test data generation methods focused on MC/DC criterion. QRS Companion Ján Cegin, Karol Rástocný, Mária Bieliková
2020	—	`conf`	Test Data Generation for MC/DC Criterion using Reinforcement Learning. ICST Workshops Ján Cegin, Karol Rástocný