English

Beyond Benchmarks: On The False Promise of AI Regulation

Machine Learning 2025-12-16 v2 Artificial Intelligence Computation and Language

Abstract

The performance of AI models on safety benchmarks does not indicate their real-world performance after deployment. This opaqueness of AI models impedes existing regulatory frameworks constituted on benchmark performance, leaving them incapable of mitigating ongoing real-world harm. The problem stems from a fundamental challenge in AI interpretability, which seems to be overlooked by regulators and decision makers. We propose a simple, realistic and readily usable regulatory framework which does not rely on benchmarks, and call for interdisciplinary collaboration to find new ways to address this crucial problem.

Keywords

Cite

@article{arxiv.2501.15693,
  title  = {Beyond Benchmarks: On The False Promise of AI Regulation},
  author = {Gabriel Stanovsky and Renana Keydar and Gadi Perl and Eliya Habba},
  journal= {arXiv preprint arXiv:2501.15693},
  year   = {2025}
}