Position: Don’t Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints

Sam Bowyer; Laurence Aitchison; Desi R. Ivanova

2025 ICML ICML 2025

Position: Don’t Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Sam Bowyer, Laurence Aitchison, Desi R. Ivanova

Topics

Artificial Intelligence > Learning Paradigms > Few-Shot Learning Machine Learning > Optimization & Theory > Statistical Learning Artificial Intelligence > Core AI > Large Language Models

Keywords

few-shot learning uncertainty quantification central limit theorem significance testing large language model error bars

Download PDF