Get started
Author

Ján Čegiň

ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness
2023 · Jan Cegin, Jakub Simko, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 31
PDF
Test Data Generation for MC/DC Criterion using Reinforcement Learning
2020 · Jan Cegin, Karol Rastocny · IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW) · 15
Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation
2024 · Jan Cegin, Branislav Pecher, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 8
PDF
LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?
2025 · Jan Cegin, Jakub Simko, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 4
PDF
Machine learning based test data generation for safety-critical software
2020 · Ján Čegiň · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · 4
A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages
2025 · Tatiana Anikina, Jan Cegin, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2
PDF
Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification
2026 · Pecher, Branislav, Spiegel, Michal, et al. · arXiv (Cornell University) · 1
PDF
RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets
2026 · Jan Cegin, Branislav Pecher, et al. · Conference of the European Chapter of the Association for Computational Linguistics · 1
PDF
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation
2024 · Branislav Pecher, Jan Cegin, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 1
PDF
Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
2026 · Association for Computational Linguistics 2026, Belanec, Robert, et al. · Underline Science Inc.
RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets
2026 · Association for Computational Linguistics 2026, Cegin, Jan, et al. · Underline Science Inc.
MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models
2026 · Association for Computational Linguistics 2026, Cegin, Jan, et al. · Underline Science Inc.
MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models
2026 · Hyben, Martin, Kula, Sebastian, et al. · arXiv (Cornell University)
PDF
Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
2026 · Pecher, Branislav, Cegin, Jan, et al. · arXiv (Cornell University)
PDF
MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models
2026 · Martin Hyben, Sebastian Kula, et al. · Findings of the Association for Computational Linguistics: EACL
PDF
Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification
2026 · Branislav Pecher, Jan Cegin, et al. · Findings of the Association for Computational Linguistics: EACL
PDF
Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
2026 · Jan Cegin, Daniil Gurgurov, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation
2025 · Jan Cegin, Branislav Pecher, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
2024 · Cegin, Jan, Pecher, Branislav, et al. · arXiv (Cornell University)
PDF
LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?
2024 · Cegin, Jan, Simko, Jakub, et al. · arXiv (Cornell University)
PDF
Synthesized dataset for search-based test data generation methods focused on MC/DC criterion
2020 · Jan Cegin, Karol Rastocny, et al. · IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)
Works count: 26
Citation count: 67
H-index: 4
I10-index: 2
Year
Topic
Type