Jan Cegin

9 papers · 2023–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (21) ❓ The Questioner

Venues

EMNLP (4) EACL (3) ACL (1) NAACL (1)

Top co-authors

Jakub Simko (9) Ivan Srba (6) Branislav Pecher (5) Maria Bielikova (4) Peter Brusilovsky (4) Robert Belanec (2) Simon Ostermann (1) Tatiana Anikina (1) Robert Moro (1) Sebastian Kula (1)

Research topics

Machine Learning (9) Natural Language Processing (7) Application Areas (6) Applications (4) Resources & Methods (4) Deep Learning (3) Generation (3) Learning Types · Machine Learning (3) Learning Types · Deep Learning (3) Artificial Intelligence (2) Learning Paradigms (2) Optimization & Theory (2)

Keywords

large language model (5) data augmentation (3) low-resource language (3) text augmentation (3) text classification (2) synthetic data generation (2) synthetic data (2) ensemble learning (1) model selection (1) cross-lingual transfer (1) intent classification (1) paraphrase generation (1) pre-trained language model (1) transfer learning (1) parameter-efficient fine-tuning (1) knowledge distillation (1) sample selection (1) noise regularization (1) model robustness (1) domain generalization (1)

Papers

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification EACL 2026 MultiCW: A Large-Scale Balanced Benchmark Dataset for Training Robust Check-Worthiness Detection Models EACL 2026 RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets EACL 2026 A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages EMNLP 2025 LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? NAACL 2025 Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation EMNLP 2025 Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation ACL 2024 Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation EMNLP 2024 ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness EMNLP 2023