Large Language Models as Markov Chains

Large language models (LLMs) are remarkably efficient across a wide range of natural language processing tasks and well beyond them. However, a comprehensive theoretical analysis of the LLMs' generali ...

Zekri Oussama, Odonnat Ambroise, Benechehab Abdelhakim, Bleistein Linus, Boullé Nicolas, Redko Ievgen

ArXiv Stat, 2025