← All lessons
MAM5020F — Generative AI for Research

LLM Deep Dive

Architecture, training, and alignment of large language models

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
Vaswani, A., et al. (2017) — NeurIPS 2017

2.2 · Training Large Language Models

Scaling Laws for Neural Language Models
Kaplan, J., et al. (2020)
Language Models are Few-Shot Learners (GPT-3)
Brown, T., et al. (2020) — NeurIPS 2020
Training Compute-Optimal Large Language Models (Chinchilla)
Hoffmann, J., et al. (2022)
GPT-4 Technical Report
OpenAI (2023)
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., et al. (2023)
The Llama 3 Herd of Models
Dubey, A., et al. (2024)

2.3 · Fine-Tuning, RLHF and Alignment

LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., et al. (2021)
Training language models to follow instructions with human feedback (InstructGPT)
Ouyang, L., et al. (2022)
Constitutional AI: Harmlessness from AI Feedback
Bai, Y., et al. (2022)
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov, R., et al. (2023) — NeurIPS 2023

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

Reading
1 min read