Empirical human-AI alignment aims to make AI systems act in line with observed human behavior. While noble in its goals, we argue that empirical alignment can inadvertently introduce statistical biases that warrant caution. This position paper thus advocates against naive empirical alignment, offering prescriptive alignment and a posteriori empirical alignment as alternatives. We substantiate our principled argument by tangible examples like human-centric decoding of language models.
@article{arxiv.2502.14581,
title = {A Statistical Case Against Empirical Human-AI Alignment},
author = {Julian Rodemann and Esteban Garces Arias and Christoph Luther and Christoph Jansen and Thomas Augustin},
journal= {arXiv preprint arXiv:2502.14581},
year = {2025}
}