Efficient and Effective In-context Demonstration Selection with Coreset
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (13) · 10458-10466
DOI: 10.1609/aaai.v40i13.38017 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zihua Wang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
In-context learning (ICL) has emerged as a powerful paradigm for Large Visual Language Models (LVLMs), enabling them to leverage a few examples directly from input contexts. However, the effectiveness of this approach is heavily reliant on the selection of demonstrations, a process that is NP-hard. Traditional strategies, including random, similarity-based sampling and infoscore-based sampling, often lead to inefficiencies or suboptimal performance, struggling to balance both efficiency and effectiveness in demonstration selection. In this paper, we propose a novel demonstration selection framework named Coreset-based Dual Retrieval (CoDR). We show that samples within a diverse subset achieve a higher expected mutual information. To implement this, we introduce a cluster-pruning method to construct a diverse coreset that aligns more effectively with the query while maintaining diversity. Additionally, we develop a dual retrieval mechanism that enhances the selection process by achieving global demonstration selection while preserving efficiency. Experimental results demonstrate that our method significantly improves the ICL performance compared to the existing strategies, providing a robust solution for effective and efficient demonstration selection.
Zitieren
APA
Wang, Z., Wang, J., Xu, H., Yan, M., Huang, F., Yang, X., Wei, X., Mi, S., & Zhang, Y. (2026). Efficient and Effective In-context Demonstration Selection with Coreset. Proceedings of the AAAI Conference on Artificial Intelligence, 40(13), 10458-10466. https://doi.org/10.1609/aaai.v40i13.38017
Vancouver
Wang Z, Wang J, Xu H, Yan M, Huang F, Yang X, et al. Efficient and Effective In-context Demonstration Selection with Coreset. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(13):10458-10466. doi:10.1609/aaai.v40i13.38017
BibTeX
@article{Wang2026,
author = {Wang, Zihua and Wang, Jiarui and Xu, Haiyang and Yan, Ming and Huang, Fei and Yang, Xu and Wei, Xiu-Shen and Mi, Siya and Zhang, Yu},
title = {Efficient and Effective In-context Demonstration Selection with Coreset},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {13},
pages = {10458--10466},
doi = {10.1609/aaai.v40i13.38017}
}
EUVIMED