# Complexity-Based Prompting

> Complexity-based prompting selects chain-of-thought exemplars that contain more reasoning steps, and at inference votes only among the sampled reasoning chains with the most steps.

- Identifier: PTL-0115
- Category: Reasoning Elicitation
- Canonical URL: https://protologue.com/t/complexity-based-prompting/
- Introduced: 2022

## Description

The method rests on the finding that demonstrations with longer, more complex reasoning improve multi-step reasoning more than simpler ones. It combines exemplar selection with a variant of self-consistency in which votes from the most complex chains count.

## Broader terms

- [Chain-of-Thought Prompting](https://protologue.com/t/chain-of-thought/)

## Related terms

- [Exemplar Selection](https://protologue.com/t/exemplar-selection/)
- [Self-Consistency](https://protologue.com/t/self-consistency/)
- [Automatic Chain-of-Thought](https://protologue.com/t/auto-cot/)

## Sources

- Fu et al. (2022). Complexity-Based Prompting for Multi-Step Reasoning. https://arxiv.org/abs/2210.00720

## Cite this entry

Protologue. (2026). Complexity-Based Prompting. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0115). https://protologue.com/t/complexity-based-prompting/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)