Efficient and Effective In-context Demonstration Selection with Coreset
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917075768836096 |
|---|---|
| author | Wang, Zihua Wang, Jiarui Xu, Haiyang Yan, Ming Huang, Fei Yang, Xu Wei, Xiu-Shen Mi, Siya Zhang, Yu |
| author_facet | Wang, Zihua Wang, Jiarui Xu, Haiyang Yan, Ming Huang, Fei Yang, Xu Wei, Xiu-Shen Mi, Siya Zhang, Yu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08977 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient and Effective In-context Demonstration Selection with Coreset Wang, Zihua Wang, Jiarui Xu, Haiyang Yan, Ming Huang, Fei Yang, Xu Wei, Xiu-Shen Mi, Siya Zhang, Yu Computer Vision and Pattern Recognition 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. |
| title | Efficient and Effective In-context Demonstration Selection with Coreset |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.08977 |