EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
Findings of the Association for Computational Linguistics: EACL 2027 [Forthcoming]
About
I am a Ph.D. student and Junior Research Fellow at the University of Tartu, advised by Prof. Kairit Sirts. I am broadly interested in Natural Language Processing (NLP). My current research is on Question Answering.
I received my MSc in Computer Science from Eötvös Loránd University, supported by the Stipendium Hungaricum scholarship, and my BSc in Information Technology and Systems Engineering from ADA University.
News
- 11/2026EstLLM has been accepted to the EACL 2027 Findings!
- 10/2026Attending the EMNLP 2026 conference in Budapest, Hungary.
- 09/2026A paper has been accepted to the UncertaiNLP 2026!
Earlier news
- 03/2026A preprint on Estonian LLM adaptation is available on arXiv.
- 02/2026Attending Workshop on Uncertainty in Machine Learning (WUML 2026).
- 11/2025Attending the EMNLP 2025 conference in Suzhou, China.
- 10/2025Awarded a Mobility Grant of the Estonian Doctoral School.
- 09/2025A paper has been accepted to the *SEM 2025 conference!
- 03/2025Attending the NoDaLiDa/Baltic-HLT 2025 conference in Tallinn.
- 02/2025TA-ing for the Natural Language Processing course.
- 09/2024Coordinating the NLP Seminar on Large Language Models.
- 07/2024Attending the ESSIR 2024 summer school at the University of Amsterdam.
- 06/2024Attending the NAACL 2024 conference in Mexico City, Mexico.
- 03/2024A paper has been accepted to the NAACL 2024 main conference!
Selected Publications
Refer, Infer, or Abstain: Investigating Latent Skill Selection of Large Language Models under Contextual Question Answering Uncertainty
Proceedings of the 3rd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2026)
Towards Evaluation of Language Models with Skill Dimensions: A Case Study on Narrative Question Answering
Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)
On Narrative Question Answering Skills
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)
Narrative Why-Question Answering: A Review of Challenges and Datasets
Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2022)
Text Similarity Detection Using Machine Learning Algorithms with Character-Based Similarity Measures 🏆 Best Paper Award
Proceedings of the 8th Machine Intelligence and Digital Interaction Conference (MIDI'2020)
Teaching
Teaching Assistant, Natural Language Processing, University of Tartu
Spring 2025
Instructor/Coordinator, NLP seminar: Large Language Models, University of Tartu
Fall 2024
Teaching Assistant, Natural Language Processing, University of Tartu
Spring 2024
Teaching Assistant, Natural Language Processing, University of Tartu
Spring 2023
Academic Service
Program Committee / Reviewer
- Conferences: ECIR 2026, NoDaLiDa/Baltic-HLT 2025, COLING 2025, ICTIR 2023
- Workshops: GEM @ACL 2026, GEM² @ACL 2025, GEM @EMNLP 2022
- ACL Rolling Review (ARR)
Thesis Defence Committee / Opponent
- Master's/Bachelor's thesis defences, Institute of Computer Science, University of Tartu (Spring 2023, Spring 2024, Spring 2026)