2 papers
cs.CR2026
Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs
Eunna Lee, Soomyoung Lee, Jungpyo Nam +6
We ask whether a model protects a user in the same way when that user speaks rather than types. Using a single distress vignette---a physical injury of unstated severity following…
cs.CR2026
Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities
Eunna Lee
When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledging its limits but by claiming…