2 papers
cs.AI2026
Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance
Allison Zhuang, Santiago Aranguri
Steering interventions targeting eval-awareness, a model's recognition that it is being tested, are increasingly used in safety evaluation pipelines, where evaluation-awareness is…
physics.soc-ph2025
Robustness of 'small' networks
Jessica Jiang, Allison C. Zhuang, Petter Holme +2
Modeling how networks change under structural perturbations can yield foundational insights into network robustness, which is critical in many real-world applications. The largest…