Testing LLM-Powered Applications - Best Practices and Evaluation Methods

Testing LLM-Powered Applications - Best Practices and Evaluation Methods

Conf42 via YouTube Direct link

Non-Determinism and Inaccuracy in LLMs

7 of 13

7 of 13

Non-Determinism and Inaccuracy in LLMs

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Testing LLM-Powered Applications - Best Practices and Evaluation Methods

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction and Welcome
  2. 2 The Challenges of LLM-Powered Applications
  3. 3 Case Study: Microsoft's Tay Bot
  4. 4 The Risks of LLMs in Real-World Applications
  5. 5 Testing LLM-Powered Applications
  6. 6 Security Concerns and Prompt Injection
  7. 7 Non-Determinism and Inaccuracy in LLMs
  8. 8 Building a Robust Test System
  9. 9 Types of Testing for LLMs
  10. 10 Metrics for Evaluating LLMs
  11. 11 Adversarial Testing and Auto Evaluation
  12. 12 Open Source Tools for LLM Testing
  13. 13 Conclusion and Final Thoughts

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.