Work

AutoEval Done Right: Using Synthetic Data for Model Evaluation

Year: 2024

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2403.07008

Authors: Boyeau, Pierre, Angelopoulos, Anastasios N., Yosef, Nir, Malik, Jitendra, Jordan, Michael I.

Institutions: University of California, Berkeley, Weizmann Institute of Science

Language: English

Topic: Machine Learning and Data Classification

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4392781612

Cites:

Cited by: 1

Related to: 10