the.ai

Reasoning / Aggregation

verified

Self-Consistency

Ask the same question several times at a temperature above zero, and take the answer that comes up most often. The reasoning paths differ; the correct answer tends to be the one they converge on, because there are many ways to reason correctly to the same place and comparatively few ways to make the same mistake twice.

Viz primitive · budget-splitextra-samples = 4

extra-samples holds 17% of the budget; rest holds the remaining 83%.

Answers drawn beyond the first, against the single sample a greedy decode would have given, in samples. Drag the sample count up to watch voting take the budget — accuracy saturates at whatever the modal answer's accuracy is, which is not one.

4

Reviewed by opendroid · 2026-08-18

  • arXiv:2203.11171 — Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • arXiv:2201.11903 — Chain-of-Thought Prompting Elicits Reasoning in Large Language Models