no code implementations • 31 Mar 2024 • Josip Jukić, Jan Šnajder
Enhancing generalization and uncertainty quantification in pre-trained language models (PLMs) is crucial for their effectiveness and reliability.
1 code implementation • 4 Oct 2023 • Fran Jelenić, Josip Jukić, Martin Tutek, Mate Puljiz, Jan Šnajder
Effective out-of-distribution (OOD) detection is crucial for reliable machine learning models, yet most current methods are limited in practical use due to requirements like access to training data or intervention in training.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +2
1 code implementation • 23 May 2023 • Josip Jukić, Jan Šnajder
Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques, particularly in low-resource domains and languages.
1 code implementation • 16 May 2023 • Fran Jelenić, Josip Jukić, Nina Drobac, Jan Šnajder
We link the AL dataset transferability to the similarity of instances queried by the different PLMs and show that AL methods with similar acquisition sequences produce highly transferable datasets regardless of the models used.
no code implementations • 1 Feb 2023 • Josip Jukić, Iva Vukojević, Jan Šnajder
Expressing attitude or stance toward entities and concepts is an integral part of human behavior and personality.
no code implementations • 20 Dec 2022 • Josip Jukić, Jan Šnajder
Developed to alleviate prohibitive labeling costs, active learning (AL) methods aim to reduce label complexity in supervised learning.
no code implementations • 15 Nov 2022 • Josip Jukić, Martin Tutek, Jan Šnajder
By connecting our findings to instance categories based on training dynamics, we show that the agreement of saliency method explanations is very low for easy-to-learn instances.
no code implementations • 11 Nov 2022 • Josip Jukić, Fran Jelenić, Miroslav Bićanić, Jan Šnajder
Supervised machine learning has become the cornerstone of today's data-driven society, increasing the need for labeled data.