Elamur Research⌕
☰
home / authors / Ivan Srba

Ivan Srba

Ivan Srba has 4 papers in our library, in 2025–2026, most of them on Language models & pretraining, Multilingual & cross-lingual NLP, Low-resource languages; often with Branislav Pecher, Maria Bielikova, Dominik Macko.

4 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 16 · 110 works · 984 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 73 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #7371

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🤝Kempelen Institute of Intelligent TechnologiesBratislava · Slovakia2020–2026 · 65 papersEmployment since 2020current🎓Brno University of TechnologyBrno · Czechia2024–2026 · 9 paperscurrent🎓Slovak University of Technology in BratislavaBratislava · Slovakia2010–2021 · 23 papersEmployment 2016–2020

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 4 worksArts and Humanities · 4 worksComputer Science · 4 worksLanguage and Linguistics · 4 works

🧭 Topics 4Research subjects and languages the work is about.Language models & pretraining · 2 worksMultilingual & cross-lingual NLP · 2 worksEvaluation & benchmarks · 1 workLow-resource languages · 1 work

 Works by year

2020s

20262 papers20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Texts (2025 · 28 citations)
    Most research on detecting machine-generated text (MGT) targets English and long, polished genres such as news or essays.
  2. Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance (2025 · 24 citations)
    The paper asks how much labelled data a small, task-specialised language model needs before it beats a large general-purpose model used without parameter updates.
  3. Automatic Combination of Sample Selection Strategies for Few-Shot Learning (2026 · 15 citations)
    Picking which labelled examples to use strongly affects few-shot performance. Methods for large language models tend to rely on selectors built for specific in-context learning setups and overlook classic strategies from supervised learning, such as active learning and core-set methods. The authors propose ACSESS…
  4. Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification (2026 · 1 citation)
    The paper asks whether a large multilingual LLM is more useful for low-resource classification as a classifier or as a source of training data for smaller models.

All works

6 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media TextsAnnual Meeting of the Association for Computational Linguistics (ACL)Dominik Macko, Jakub Kopál, Robert Moro, et al.2025 · 28 citations
  2. Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even PerformanceConference on Empirical Methods in Natural Language Processing (EMNLP)Branislav Pecher, Ivan Srba, Maria Bielikova2025 · 24 citations
  3. Authorship Obfuscation in Multilingual Machine-Generated Text Detection ↗Findings of the Association for Computational Linguistics: EMNLP 2024 · no summary yetDominik Macko et al.2024 · 24 citations
  4. A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts ↗Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetNafis Irtiza Tripto et al.2024 · 24 citations
  5. Automatic Combination of Sample Selection Strategies for Few-Shot LearningFindings of the Association for Computational LinguisticsBranislav Pecher, Ivan Srba, Maria Bielikova, et al.2026 · 15 citations
  6. Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual ClassificationFindings of the Association for Computational LinguisticsBranislav Pecher, Jan Cegin, Robert Belanec, et al.2026 · 1 citation

 Co-authors here

7 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 73 times (of the 149,439 papers whose bibliographies we read); 13 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ivan-srba/