Skip to content

In-Context Learning

Definition
AI-generated

In-context learning is the ability of a large language model to adapt its behavior from examples or instructions placed in the prompt (the “context”) without gradient updates—sometimes called few-shot or many-shot prompting when several labeled examples are provided.

Topics
LLM and Agents
Related
Context Context Engineering Context Window

Why it matters in GWAS

Few-shot prompts can standardize extraction of fields from heterogeneous supplementary tables or map free-text phenotypes to ontologies, but performance varies by model and prompt; evaluation on held-out curated examples reduces silent failure modes.

Example usage

"A replication analysis checks whether In-Context Learning assumptions hold across cohorts."

Context Context Engineering Context Window Large Language Model (LLM) Prompt Engineering Prompt Learning Retrieval-Augmented Generation (RAG)
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Brown T, et al. (2020). Language models are few-shot learners. NeurIPS.
← Imputation Reference Panel In-paralog →

Last updated (UTC · Git history)