How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation

Documenti analoghi

• Robust Conformal Prediction Using Privileged Information
  di: Feldman, Shai, et al.
  Pubblicazione: (2024)
• Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
  di: Feldman, Shai, et al.
  Pubblicazione: (2025)
• Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
  di: Davidov, Hen, et al.
  Pubblicazione: (2025)
• Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
  di: Tolochinsky, Elad, et al.
  Pubblicazione: (2026)
• Automating Deception: Scalable Multi-Turn LLM Jailbreaks
  di: Kumarappan, Adarsh, et al.
  Pubblicazione: (2025)