📚 Bibliography: LLM Applications and Safety

This bibliography complements Chapter 8 by focusing on applied large language models: how we steer them, evaluate them, and deploy them safely.

Prompting and tool use

• Lilian Weng (OpenAI). Prompt Engineering.
• Anthropic. Constitutional AI.

Post-training: instruction tuning and alignment

• Ouyang et al. (2022). Training language models to follow instructions with human feedback (InstructGPT).
• Bai et al. (2022). Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Evaluation, reliability, and safety

• OpenAI. Evals.
• Ribeiro et al. (2020). Beyond Accuracy: Behavioral Testing of NLP Models with CheckList.

Privacy and deployment considerations

• NIST. AI Risk Management Framework (AI RMF 1.0).