AAAI 2026technical0 citations

Confirmation Bias: A Challenge for Scalable Oversight

Gabriel Recchia, Chatrik Singh Mangat, Jinu Nyachhyon, Mridul Sharma, Callum Canavan, Dylan Epstein-Gross, Muhammed Abdulbari

Abstract

Scalable oversight protocols aim to empower evaluators to verify outputs of AI models more capable than themselves. However, human evaluators

BibTeX
@inproceedings{aaai2026_confirmationbias,
  title = {Confirmation Bias: A Challenge for Scalable Oversight},
  author = {Gabriel Recchia and Chatrik Singh Mangat and Jinu Nyachhyon and Mridul Sharma and Callum Canavan and Dylan Epstein-Gross and Muhammed Abdulbari},
  booktitle = {AAAI 2026},
  year = {2026}
}
Confirmation Bias: A Challenge for Scalable Oversight · AAAI 2026