Ján Čegiň

Publications

• 2024

  ČEGIŇ Ján, PECHER Branislav, ŠIMKO Jakub, SRBA Ivan and BIELIKOVÁ Mária. Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Bangkok: Association for Computational Linguistics, 2024, pp. 13148-13171. ISBN 979-8-8917-6094-3.
  Detail

  PECHER Branislav, ČEGIŇ Ján, BELANEC Róbert, SRBA Ivan, ŠIMKO Jakub and BIELIKOVÁ Mária. Fighting Randomness With Randomness: Mitigating Optimisation Instability of Fine-Tuning Using Ensemble and Noise Regularisation. In: Findings of the Association for Computational Linguistics: EMNLP 2024. Miami: Association for Computational Linguistics, 2024, pp. 11005-11044. ISBN 979-8-8917-6168-1.
  Detail

• 2023

  ČEGIŇ Ján and ŠIMKO Jakub. ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Singapur: Association for Computational Linguistics, 2023, pp. 1889-1905. ISBN 979-8-8917-6060-8.
  Detail

• 2022

  ČEGIŇ Ján. A Game for Crowdsourcing Adversarial Examples for False Information Detection. In: CEUR Workshop Proceedings. Vídeň: CEUR-WS.org, 2022, pp. 13-25. ISSN 1613-0073.
  Detail