In-Context Learning

A model's ability to acquire task behavior from instructions and examples placed in the prompt at inference time, without any weight updates.

grounded in: Trend theme 'Interpretability and causal reasoning about LLMs' (appetite for mechanistic accounts of what models actually do inside) — the foundational inference-time-learning phenomenon those account

Connected concepts

Prompt engineering, Chain-of-Thought, Context engineering, Long-horizon agency