Exemplar Selection
Also called demonstration selection, dynamic few-shot, kNN prompting.
Exemplar selection is the choice of which demonstrations to include in a few-shot prompt, commonly by retrieving the examples most semantically similar to the current input.
Description
Liu et al. showed that retrieving nearest-neighbor examples by embedding similarity outperformed random selection. Selection can also target diversity, difficulty, or the model's uncertainty, as in active prompting.
Sources
- Liu et al. (2021). What Makes Good In-Context Examples for GPT-3?.
Cite this entry
Protologue. (2026). Exemplar Selection. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0019). https://protologue.com/t/exemplar-selection/
BibTeX
@misc{protologue_exemplar_selection,
title = {Exemplar Selection},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0019},
url = {https://protologue.com/t/exemplar-selection/}
}