English

AutoEval Done Right: Using Synthetic Data for Model Evaluation

Machine Learning 2024-05-29 v2 Artificial Intelligence Computation and Language Methodology

Abstract

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process called autoevaluation. We suggest efficient and statistically principled algorithms for this purpose that improve sample efficiency while remaining unbiased. These algorithms increase the effective human-labeled sample size by up to 50% on experiments with GPT-4.

Keywords

Cite

@article{arxiv.2403.07008,
  title  = {AutoEval Done Right: Using Synthetic Data for Model Evaluation},
  author = {Pierre Boyeau and Anastasios N. Angelopoulos and Nir Yosef and Jitendra Malik and Michael I. Jordan},
  journal= {arXiv preprint arXiv:2403.07008},
  year   = {2024}
}

Comments

New experiments, fix fig 1

R2 v1 2026-06-28T15:16:12.934Z