## Table of Contents

- [Technique 1: Supervised learning](/content/up/ai-model-training-techniques#rebelltitem1/index.html)
- [Technique 2: Reinforcement learning from human feedback (RLHF)](/content/up/ai-model-training-techniques#rebelltitem2/index.html)
- [Technique 3: Model evaluation](/content/up/ai-model-training-techniques#rebelltitem3/index.html)
- [Technique 4: Red teaming](/content/up/ai-model-training-techniques#rebelltitem4/index.html)
- [Technique 5: Quality assurance (QA)](/content/up/ai-model-training-techniques#rebelltitem5/index.html)
- [Why domain-expert annotators outperform crowd workers](/content/up/ai-model-training-techniques#rebelltitem6/index.html)
- [Glossary](/content/up/ai-model-training-techniques#rebelltitem7/index.html)
- [FAQ](/content/up/ai-model-training-techniques#rebelltitem8/index.html)

### Author

[Marcelo Teo](/content/u/marceloteo/index.html)