In-Context Learning
Also called ICL.
In-context learning (ICL) is a language model's ability to perform a task by conditioning on instructions or demonstrations in its prompt, without any update to its weights.
Description
Identified as an emergent capability of large pretrained models in the GPT-3 paper, ICL underlies few-shot prompting. Studies show that models often rely more on the format and label space of demonstrations than on whether the demonstration labels are correct.
Sources
- Brown et al. (2020). Language Models are Few-Shot Learners.
Cite this entry
Protologue. (2026). In-Context Learning. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0017). https://protologue.com/t/in-context-learning/
BibTeX
@misc{protologue_in_context_learning,
title = {In-Context Learning},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0017},
url = {https://protologue.com/t/in-context-learning/}
}