Prompting techniques
Self-consistency
Definition
Self-consistency runs the same reasoning prompt several times at non-zero temperature and takes the most common answer. It trades cost for accuracy on problems with a single verifiable result.
The insight is that incorrect reasoning tends to fail in varied ways while correct reasoning converges. Sample five chains of thought for an arithmetic problem and the right answer will often appear more frequently than any individual wrong one, even when a single run is unreliable.
It only applies where answers can be compared for equality — numerical results, classifications, extracted fields. It does not work for open-ended generation, where five good essays are simply five different essays.
Cost scales linearly with sample count, so this is a technique for high-stakes, low-volume decisions rather than bulk processing.
Related terms
Chain-of-thought prompting
Chain-of-thought prompting asks a model to work through its reasoning step by step before answering. It measurably improves accuracy on maths, logic, and multi-step problems by forcing intermediate steps instead of an immediate guess.
Temperature
Temperature controls how random a model's word choices are. Low values (0-0.3) make output focused and repeatable; high values (0.8-1.2) make it more varied and creative but less reliable.
Tree-of-thought
Tree-of-thought extends chain-of-thought by exploring several reasoning branches in parallel, evaluating each, and pursuing the most promising. It helps on problems where the first plausible path is often wrong.
Zero-shot prompting
Zero-shot prompting means asking a model to do a task with no worked examples — just an instruction. It works well for common tasks the model has seen extensively in training.
Few-shot prompting
Few-shot prompting means including two to five worked examples of the input-output pattern you want before making your real request. It is the fastest way to lock in a consistent format, tone or edge-case behaviour.
Meta-prompting
Meta-prompting is using a model to write, critique or improve prompts. You describe the task and the failure modes you want to avoid, and the model drafts the prompt.
Put this into practice
Understanding the term is step one. Our free courses and tools let you actually use it.