Prompt Optimization via Adversarial In-Context Learning

Documenti analoghi

• Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
  di: Zhao, Yiran, et al.
  Pubblicazione: (2024)
• Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
  di: Brown, Hannah, et al.
  Pubblicazione: (2024)
• In-Context Reinforcement Learning for Tool Use in Large Language Models
  di: Ye, Yaoqi, et al.
  Pubblicazione: (2026)
• Single Character Perturbations Break LLM Alignment
  di: Lin, Leon, et al.
  Pubblicazione: (2024)
• Reasoning Robustness of LLMs to Adversarial Typographical Errors
  di: Gan, Esther, et al.
  Pubblicazione: (2024)