This work proposes ForeSight, a first-token output-risk forecasting framework that distills weak and redundant early safety signals into compact, layer-aware risk representations and achieves superior and efficient early-risk forecasting while relying solely on first-token hidden states.
Han-Lin Wang, Chen-Long Wei, Ling Xu et al.· 0 citations
The Consistency Radius is introduced, a metric that quantifies the maximum distribution shift under which an audit conclusion based on a third-party dataset remains consistent, and a convex relaxation-based optimization method to estimate the radius using only model responses over the audit dataset is proposed.
Yuan-Hao Liu, Qi Cao, Hua-Wei Shen· Proceedings of the Thirty-Fi...· 0 citations
RecVerse is presented, a GUI-grounded simulation agent that perceives pages through screenshots and produces faithful multi-turn trajectories and significantly outperforms existing baselines in both behavioral fidelity and intent consistency.
Jia-Kai Tang, Yan Mi, Jing Yu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.