Safety Beyond the Interface: Detecting Harm via Latent LLM States

2026

View at publisher
Authors: Alizishaan Khatri, Chiquita Prabhu, Omkar Neogi
DOI: 10.13140/rg.2.2.29352.64005
Cited by: 0

Fields of Study & Subjects

Adversarial Robustness in Machine Learning Ethics and Social Impacts of AI Safety Systems Engineering in Autonomy

Publication details

Publication date
1 January 2026
Language
EN