Zum Inhalt springen
AI Learning

Sources & Further Reading

iSources checked: September 2026

The content of this module was researched in May 2026; all source links were checked for availability in September 2026 and updated where needed. As the AI landscape evolves quickly, some details may have changed since then.

Sources

  1. Vaswani, A. et al. (2017). Attention Is All You Need. arXiv:1706.03762. https://arxiv.org/abs/1706.03762

  2. Mikolov, T. et al. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv:1301.3781. https://arxiv.org/abs/1301.3781

  3. Ouyang, L. et al. (2022). Training language models to follow instructions with human feedback. arXiv:2203.02155. https://arxiv.org/abs/2203.02155

  4. Bai, Y. et al. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073. https://arxiv.org/abs/2212.08073

  5. Rafailov, R. et al. (2023). Direct Preference Optimization: Your Language Model is Secretly a Reward Model. arXiv:2305.18290. https://arxiv.org/abs/2305.18290

  6. Shanahan, M. (2023). Talking about Large Language Models. Communications of the ACM / arXiv:2212.03551. Foundation for the "LLMs as role simulators" mental model — argues for precise language when talking about LLMs and against inadvertently attributing intentionality. https://arxiv.org/abs/2212.03551

  7. Shanahan, M., McDonell, K., Reynolds, L. (2023). Role play with large language models. Nature 623, 493–498. The scientific basis for the author-character framing used in the "Mental Model" section. https://www.nature.com/articles/s41586-023-06647-8

Further Reading

Videos & Visual Explanations

Interactive Tools

  • Transformer Explainer (Polo Club, Georgia Tech): Runs a real GPT-2 model in the browser and shows every computation step -- from tokenisation to the probability distribution. The inspiration for the interactive visualisations in this module. https://poloclub.github.io/transformer-explainer/

Articles & Tutorials

Courses