Position: AI Evaluation Should Work With Humans

Jan Kulveit; Gavin Leech; Tomáš Gavenčiak; Raymond Douglas

ICML 2026poster0 citations

Position: AI Evaluation Should Work With Humans

Jan Kulveit, Gavin Leech, Tomáš Gavenčiak, Raymond Douglas

Abstract

We argue that the dominant paradigm of AI evaluation, which focuses on autonomous superhuman performance and so an implicit goal of replacing humans, is guiding AI development in the wrong direction. Instead, the AI community should pivot to evaluating the performance of human–AI teams. We argue that this collaborative shift in evaluation will foster AI systems that act as true complements to human capabilities and therefore lead to far better societal outcomes than the current process.

Benchmark

BibTeX

@inproceedings{icml2026_positionaievalua,
  title = {Position: AI Evaluation Should Work With Humans},
  author = {Jan Kulveit and Gavin Leech and Tomáš Gavenčiak and Raymond Douglas},
  booktitle = {ICML 2026},
  year = {2026}
}