Self-Consistency
Also called majority voting, CoT-SC.
Self-consistency samples multiple chain-of-thought reasoning paths for the same question and returns the answer that appears most often, rather than relying on a single greedy decode.
Description
Wang et al. found this majority vote substantially improved chain-of-thought accuracy on arithmetic and commonsense benchmarks. It trades extra inference cost for reliability and is an early form of test-time compute scaling.
Sources
- Wang et al. (2022). Self-Consistency Improves Chain of Thought Reasoning in Language Models.
Cite this entry
Protologue. (2026). Self-Consistency. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0028). https://protologue.com/t/self-consistency/
BibTeX
@misc{protologue_self_consistency,
title = {Self-Consistency},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0028},
url = {https://protologue.com/t/self-consistency/}
}