Definition
Plain language
A trick where you have the model answer the same question several times and take the majority answer.
As stated in the literature
A test-time technique that samples multiple chain-of-thought completions and aggregates final answers via majority vote.
Why it matters: It often improves accuracy substantially with no training changes, at the cost of using more inference compute per question.
For example, ask the model to solve a math problem ten times with sampling temperature on, and report whichever final answer shows up most often.
Heard on the show
“We'll link it in the show notes alongside the related background reading on Self-Refine, Self-Consistency, and the original Parallel-Distill-Refine work.”Episode 003 — How to Pick the Best of Sixteen Coding Agent Rollouts