#artificial intelligence
Sep 2026
When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning
This work studies failure disclosure: whether a model admits that an attempted solution failed rather than staying silent or presenting it as successful, and makes reporting substantially more consistent, though its effect on task performance depends on the setting.
Steven Y. Feng, Noah D. Goodman, Michael C. Frank et al.
· arXiv.org · 0 citations