AutoEval Done Right: Using Synthetic Data for Model Evaluation

arXiv:2403.07008v1 Announce Type: new
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.

abstract algorithms annotations arxiv cs.ai cs.cl cs.lg data evaluation human machine machine learning machine learning models process stat.me synthetic synthetic data type validation