Demonstration Label Sensitivity
Also called role of demonstrations.
Demonstration label sensitivity refers to how much a model's few-shot performance depends on whether the example labels are correct; research found that randomly replacing labels often hurts performance only slightly.
Description
Min et al. showed that demonstrations mainly supply the label space, the input distribution, and the format of the task. This suggests few-shot examples work largely by specifying what the task looks like rather than by teaching the input-label mapping.
Sources
- Min et al. (2022). Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?.
Cite this entry
Protologue. (2026). Demonstration Label Sensitivity. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0018). https://protologue.com/t/demonstration-label-sensitivity/
BibTeX
@misc{protologue_demonstration_label_sensitivity,
title = {Demonstration Label Sensitivity},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0018},
url = {https://protologue.com/t/demonstration-label-sensitivity/}
}