Preprint
A Second Sample Is Not a Second Signal: What the One-Sample Semantic Entropy Result Measures, Why the Sampling Premium Is Mostly a Disagreement About the Baseline, and the Matched Comparison That Would Settle It
Life of Research Semantic entropy detects confabulations in language models by drawing several answers, grouping them by meaning and measuring how spread the meanings are. Because each extra answer costs a full generation, a line of work asks how few samples will do. A 2025 Bayesian estimator…