Lecture 7 Additional Software Tools

• garak
• PyRIT

Lecture 7 Additional Resources

• Cataloguing LLM Evaluations
• Generative AI Risk Management Resources
• LLM Security and Privacy
• PAI’s Responsible Practices for Synthetic Media

Lecture 7 Additional Reading

• Introduction and Background:

  • Taxonomy of Risks posed by Language Models
  • On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?

• Technical Information:

  • DQI: Measuring Data Quality in NLP
  • The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources