@pierreboyeau.bsky.social
Pleased to announce that our paper, "AutoEval Done Right: Using Synthetic Data for Model Evaluation," has been accepted to ICML 2025!
AutoEval Done Right: Using Synthetic Data for Model Evaluation
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 req...
arxiv.org
May 5, 2025 at 12:24 AM
Pleased to announce that our paper, "AutoEval Done Right: Using Synthetic Data for Model Evaluation," has been accepted to ICML 2025!