MAM5020F — Generative AI for Research
LLM Deep Dive
Architecture, training, and alignment of large language models
Contents
11 arXiv papers covering transformers, scaling laws, instruction tuning, RLHF, and the major open and closed model families.
Each entry links to the canonical version of the paper: on arXiv, the journal, or the publisher. Where a paper is paywalled, the DOI is given for UCT-library access.
2.1 · LLM Architecture Deep Dive
Attention Is All You Need
2.2 · Training Large Language Models
Scaling Laws for Neural Language Models
Language Models are Few-Shot Learners (GPT-3)
Training Compute-Optimal Large Language Models (Chinchilla)
GPT-4 Technical Report
Llama 2: Open Foundation and Fine-Tuned Chat Models
The Llama 3 Herd of Models
2.3 · Fine-Tuning, RLHF and Alignment
LoRA: Low-Rank Adaptation of Large Language Models
Training language models to follow instructions with human feedback (InstructGPT)
Constitutional AI: Harmlessness from AI Feedback
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
2.4 · How AI Image Generation Works
Explanatory content only. No primary papers in this sub-lesson.
Drafted with Claude (Anthropic) and reviewed by Jonathan Shock before publication. AI-generated errors are possible — if you spot one, please email jonathan.shock@uct.ac.za. Full detail: AI Content Disclaimer.
© 2026 Jonathan Shock · MAM5020F: Generative AI for Research · CC BY 4.0