Scaling laws

Emergent abilities

Instruction tuning

Reinforcement Learning from Human Feedback (RLHF)

Prompt engineering

Chain-of-thought prompting

In-context learning

Retrieval-Augmented Generation (RAG)

Hallucination & factuality

Model interpretability & explainability

Parameter-efficient fine-tuning (LoRA, adapters, prefix tuning)

Quantization & model compression