AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Efficient and Effective In-context Demonstration Selection with Coreset

Zihua Wang, Jiarui Wang, Haiyang Xu, Ming Yan, Fei Huang, Xu Yang, Xiu-Shen Wei, Siya Mi, Yu Zhang

AAAI 2026 · Large language models › Language, safety and interpretability · approach: In-context learning analysis · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use cluster-pruning coreset instead of random coreset (ablation)CoDR · MSCOCO captioning 4-shot (OFv2)CIDEr: 80.12 -> 104.23Improved
use cluster-pruning coreset instead of centroid coreset (ablation)CoDR · MSCOCO captioning 4-shot (OFv2)CIDEr: 101.09 -> 104.23Improved
use cluster-pruning coreset instead of centroid coreset (ablation)CoDR · Stanford Dogs FIC 4-shot (IDEv2)accuracy: 63.56 -> 66.28Improved
use dual retrieval over full support set instead of random pick in coreset (ablation)CoDR · VQAv2 4-shot (OFv2)accuracy: 43.58 -> 53.49Improved
use dual retrieval instead of similarity pick in coreset (ablation)CoDR · Stanford Dogs FIC 4-shot (OFv2)accuracy: 36.47 -> 41.39Improved
use dual retrieval instead of diversity-only pick in coreset (ablation)CoDR · Stanford Dogs FIC 4-shot (OFv2)accuracy: 24.44 -> 41.39Improved
use dual retrieval instead of similarity pick in coreset (ablation)CoDR · VQAv2 4-shot (IDEv2)accuracy: 66.33 -> 67.01No clear effect
larger coreset beyond about 50 for IC/VQA (ablation)CoDR · IC and VQACIDEr / accuracyNo clear effect
coreset smaller than the 120 classes (ablation)CoDR · Stanford Dogs FICaccuracyHurt
use similarity-based retrieval instead of randomSimilarity retrieval (SITR) · MSCOCO captioning (OFv2) 1-shotCHAIRi: 7.9 -> 14.35Hurt
use CoDR instead of infoscore-local retrievalCoDR · MSCOCO captioning (OFv2)time per query (s): 13.78 -> 3.95Improved
use CoDR instead of similarity-based retrieval (SITR)CoDR · MSCOCO captioning (OFv2)CIDEr 4-shot: 97.29 -> 104.23Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy