Prompt Engineering
lilianweng.github.io- Category
- Other
- Type
- ARTICLE
- Builder
- @lilianweng
- Added
- Jul 21, 2026
About
Prompt Engineering , also known as In-Context Prompting , refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy experimentation and heuristics. This post only focuses on prompt engineering for autoregressive language models, so nothing with Cloze tests, image generation or multimodality models. At its
Why it made the leaderboard
A rigorous, practitioner-oriented survey of in-context prompting methods — few-shot, chain-of-thought, self-consistency, and more — that explains not just what works but the empirical reasoning behind steering LLM behavior without fine-tuning.
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.