Skip to Main Content
Reliabilitype-citation-107P1

Self-consistency decoding with majority voting improves CoT reliability.

Sampling multiple CoT paths and taking…Sampling multiple CoT paths and taking the majority answer boosted GSM8K accuracy from 58.1% to 74.4% on PaLM 540B — a 28% relative improvement over single-path CoT.

Context & Methodology

Self-consistency works by generating multiple diverse reasoning chains and selecting the most consistent final answer, reducing the impact of individual reasoning errors.

Applies To

openaianthropicgoogle

Confidence Level

High

Implementation Effort

medium

Recommendation

follow

Execution Priority

P1

Put This Evidence to Work

Use the STCO framework to implement findings like this in structured, testable prompts.

Structured prompt templates cut development time from 4 hours to 20 minutes per prompt (8x reduction) by separating inst.LangChain, 'Prompt Templates' documentation, 2024