Róbert Belanec

According to our database, Róbert Belanec authored at least 7 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification.

Branislav Pecher, Michal Spiegel, Róbert Belanec, Ján Cegin

CoRR, February, 2026

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification.

Branislav Pecher, Ján Cegin, Róbert Belanec, Ivan Srba, Jakub Simko, Mária Bieliková

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models.

Róbert Belanec, Ivan Srba, Mária Bieliková

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark.

Róbert Belanec, Branislav Pecher, Ivan Srba, Mária Bieliková

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

2025

Task Prompt Vectors: Effective Initialization Through Multi-task Soft Prompt Transfer.

Róbert Belanec, Simon Ostermann, Ivan Srba, Mária Bieliková

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track and Applied Data Science Track, 2025

2024

Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation.

Branislav Pecher, Ján Cegin, Róbert Belanec, Jakub Simko, Ivan Srba, Mária Bieliková

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024

2023

Controlling the Output of a Generative Model by Latent Feature Vector Shifting.

Róbert Belanec, Peter Lacko, Kristína Malinovská

CoRR, 2023