SafePassage: High-Fidelity Information Extraction with Black Box LLMs

Documenti analoghi

• PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations
  di: Salimian, Sina, et al.
  Pubblicazione: (2025)
• Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
  di: Li, Changhao, et al.
  Pubblicazione: (2024)
• Towards Universal and Black-Box Query-Response Only Attack on LLMs with QROA
  di: Jawad, Hussein, et al.
  Pubblicazione: (2024)
• In-Context Explainers: Harnessing LLMs for Explaining Black Box Models
  di: Kroeger, Nicholas, et al.
  Pubblicazione: (2023)
• Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs
  di: Hartmann, David, et al.
  Pubblicazione: (2026)