Year: 2026
Type: conference-paper
Abstract: 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 strategies specifically tailored to individual in-context learning settings.In this paper, we propose a new method for Automatic Combination of SamplE Selection Strategies (ACSESS) to leverage the strengths and complementarity of various well-established selection objectives.We investigate and compare the impact of 23 sample selection strategies on the performance of 5 in-context learning models and 3 few-shot learning approaches (meta-learning, few-shot fine-tuning) over 6 text and 8 image datasets.The experimental results show that the combination of strategies through the ACSESS method consistently outperforms all individual selection strategies and performs on par or exceeds the in-context learning specific baselines.Lastly, we demonstrate that sample selection remains effective even on smaller datasets, yielding the greatest benefits when only a few shots are selected, while its advantage diminishes as the number of shots increases.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G182602407, vera.ai: VERification Assisted by Artificial Intelligence, G2592723113, G434337789, G5378839026, G6816971739, G6948331134, AI-CODE - AI services for COntinuous trust in emerging Digital Environments, G7758855706, Multimodálna detekcia prejavov toxického správania v sociálnych médiách, Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization
OpenAlex ID: W4391622449