Ivan Srba

A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness

2023 · arXiv (Cornell University)

Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-learning or few-shot learning, aims to effectively train a model using only a small amount of labelled samples. However, these approaches have been observed …

Automatic Combination of Sample Selection Strategies for Few-Shot Learning

2026

In few-shot learning, the selection of samples has a significant impact on the performance of the model.While effective sample selection strategies are well-established in supervised settings, research on large language models largely overlooks them, favouring …

A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness

2024 · ACM Computing Surveys

Learning with limited labelled data, such as prompting, in-context learning, fine-tuning, meta-learning, or few-shot learning, aims to effectively train a model using only a small amount of labelled samples. However, these approaches have been observed …