Method2025-08-25#reliability
Sample many, keep the majority
Different samples take different reasoning paths but tend to converge on the same correct answer, while the wrong answers scatter. Voting over the final answers turns that asymmetry into accuracy.
It costs you N times the compute, so reserve it for the questions that matter. A useful middle ground is to escalate to self-consistency only when the first answer looks low-confidence.
Aha moment
Wrong reasoning paths tend to scatter; correct reasoning paths often converge.
Try this
Sample several answers, normalize the final claim, and inspect disagreement before majority voting.
Watch for
- Repeated wording counted as independent evidence
- Voting over outputs that all share the same missing assumption
- Compute spent on low-value questions