In-context learning: zero-shot and few-shot prompting
How in-context learning (ICL) lets a frozen language model do a new task from a few examples in its prompt, with patterns, verbalizers and no weight updates.
Part of Large language models.
Read next
- Calibrate before use: contextual calibration for LLMs
Why few-shot accuracy swings with example order (majority label and recency bias), and how contextual calibration with an "N/A" input divides the lean out.