Entities · Labs
GPT
5 articles tagged with this entity.
-
Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety
-
Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
-
Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond
-
RAG over Thinking Traces Can Improve Reasoning Tasks
-
Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models