2024/06/14 by Olivier Binette, Jerome P. Reiter, Binette, Olivier +1 · 3 citations
Computer Science · Decision Sciences · Medicine · #Applications (stat.AP) #Artificial Intelligence in Healthcare and Education #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Impact of AI and Big Data on Business and Society #Machine Learning (cs.LG) #Methodology (stat.ME)
paper · pdf · doi:10.48550/arxiv.2406.10366
openalex publication_date 2024/06/14 · openalex created_date 2024/06/19 · openalex updated_date 2026/07/28
Commonly, AI or machine learning (ML) models are evaluated on benchmark datasets. This practice supports innovative methodological research, but benchmark performance can be poorly correlated with performance in real-world applications -- a construct validity issue. To improve the validity and practical usefulness of evaluations, we propose using an estimands framework adapted from international clinical trials guidelines. This framework provides a systematic structure for inference and reporting in evaluations, emphasizing the importance of a well-defined estimation target. We illustrate our proposal on examples of commonly used evaluation methodologies - involving cross-validation, clustering evaluation, and LLM benchmarking - that can lead to incorrect rankings of competing models (rank reversals) with high probability, even when performance differences are large. We demonstrate how the estimands framework can help uncover underlying issues, their causes, and potential solutions. Ultimately, we believe this framework can improve the validity of evaluations through better-aligned inference, and help decision-makers and model users interpret reported results more effectively.