Voting over sampled answers

Compute exactly how majority voting over n sampled answers changes accuracy, and see when it helps and when it hurts.

AdvancedExplained in Thinking longer

Majority vote over sampled answers

If each sampled chain of thought is right with probability p, how often is the most common answer among n samples right?

40%
9
Possible answers
One sample right40%
Vote of 9 right (exact)59.9%
Simulated, 1,000 votesNot run yet

Try this

  • With 2 answers, compare p = 60% with p = 40% as n grows.
  • With 4 answers, keep p below 50% and compare spread-out wrong answers with one tempting wrong answer.
  • Run 1,000 votes and check the simulation against the exact curve.

The curve assumes independent samples. Real samples from one model make correlated mistakes, so real gains are smaller.

Try "embedding", "softmax", "overfitting", or "backpropagation".