The framework and EvalAwareBench provide the tools to measure, attribute, and mitigate evaluation awareness, building the foundation for future solutions to ground evaluation awareness in social psychology.
Changling Li, Terry Jingchen Zhang, Jie M. Zhang et al.· arXiv.org· 1 citation
It is found that standard supervised fine-tuning can rapidly suppress valid reasoning traces, and that answer-only metrics can substantially obscure this failure: in several settings, performance conditional on valid reasoning remains high while the rate of valid reasoning falls sharply.
Lukas Twist, Helen Yannakoudakis, Jie M. Zhang· arXiv.org· 4 citations
WorldCycle is introduced, a self-verifiable RL framework that constructs closed action cycles and their repeated executions from ordinary action sequences, and optimizes two complementary rewards: a spatial closure reward enforcing symmetry between mirrored forward and reverse segments, and a temporal consistency rewar...
Bohai Gu, Yueyang Yuan, Tai-Yi Wu et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.