Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models

Documenti analoghi

• Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems
  di: Klisura, Đorđe, et al.
  Pubblicazione: (2024)
• A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems
  di: Klisura, Đorđe, et al.
  Pubblicazione: (2025)
• STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning
  di: Bharadwaj, Aryasomayajula Ram
  Pubblicazione: (2025)
• Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
  di: Jain, Neel, et al.
  Pubblicazione: (2024)
• Measuring and Eliminating Refusals in Military Large Language Models
  di: FitzGerald, Jack, et al.
  Pubblicazione: (2026)