AI RESEARCH
UCS: Estimating Unseen Coverage for Improved In-Context Learning
arXiv CS.LG
•
ArXi:2604.12015v1 Announce Type: new In-context learning (ICL) performance depends critically on which nstrations are placed in the prompt, yet most existing selectors prioritize heuristic notions of relevance or diversity and provide limited insight into the coverage of a nstration set. We propose Unseen Coverage Selection (UKS), a