Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models

Documenti analoghi

• When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
  di: Petrov, Aleksandar, et al.
  Pubblicazione: (2023)
• Universal In-Context Approximation By Prompting Fully Recurrent Models
  di: Petrov, Aleksandar, et al.
  Pubblicazione: (2024)
• Prompting a Pretrained Transformer Can Be a Universal Approximator
  di: Petrov, Aleksandar, et al.
  Pubblicazione: (2024)
• Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models
  di: Zhang, Wenxuan, et al.
  Pubblicazione: (2024)
• Efficient Error Certification for Physics-Informed Neural Networks
  di: Eiras, Francisco, et al.
  Pubblicazione: (2023)