AIbase
Product LibraryTool NavigationMCP

Optimal-Demo-Selection-ICL

Public

Implements and benchmarks optimal demonstration selection strategies for In-Context Learning (ICL) using LLMs. Covers IDS, RDES, Influence-based Selection, Se², and TopK+ConE across reasoning and classification tasks, analyzing the impact of example relevance, diversity, and ordering on model performance across multiple architectures.

Creat2025-04-02T21:03:11
Update2025-05-01T10:42:16
https://github.com/SatvikPraveen/Optimal-Demo-Selection-ICL
0
Stars
0
Stars Increase

Related projects