most citedMitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework

17 citations · 17 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

Amit Roth, Ankur Samanta, Matan Halevy +2

Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful und…