Chatgpt to replace crowdsourcing of paraphrases for intent classification: Higher diversity and comparable model robustness J Cegin, J Simko, P Brusilovsky Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023 | 42 | 2023 |
Test data generation for MC/DC criterion using reinforcement learning J Čegiň, K Rástočný 2020 IEEE international conference on software testing, verification and …, 2020 | 15 | 2020 |
Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation J Cegin, B Pecher, J Simko, I Srba, M Bielikova, P Brusilovsky Proceedings of the 62nd Annual Meeting of the Association for Computational …, 2024 | 8 | 2024 |
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation B Pecher, J Cegin, R Belanec, J Simko, I Srba, M Bielikova Findings of the Association for Computational Linguistics: EMNLP 2024, 11005 …, 2024 | 3 | 2024 |
LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? J Cegin, J Simko, P Brusilovsky arXiv preprint arXiv:2408.16502, 2024 | 2 | 2024 |
Machine learning based test data generation for safety-critical software J Čegiň Proceedings of the 28th ACM Joint Meeting on European Software Engineering …, 2020 | 2 | 2020 |
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification J Cegin, B Pecher, J Simko, I Srba, M Bielikova, P Brusilovsky arXiv preprint arXiv:2410.10756, 2024 | 1 | 2024 |
A Game for Crowdsourcing Adversarial Examples for False Information Detection J Cegin, J Simko, P Brusilovsky AIofAI ‘22: 2nd Workshop on Adverse Impacts and Collateral Effects of …, 2022 | | 2022 |
Synthesized dataset for search-based test data generation methods focused on MC/DC criterion J Čegiň, K Rástočný, M Bieliková 2020 IEEE 20th International Conference on Software Quality, Reliability and …, 2020 | | 2020 |