Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.04412 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908866672852992 |
|---|---|
| author | Usatenko, O. V. Melnyk, S. S. Pritula, G. M. |
| author_facet | Usatenko, O. V. Melnyk, S. S. Pritula, G. M. |
| contents | Large-scale language models (LLMs) operate in extremely high-dimensional state spaces, where both token embeddings and their hidden representations create complex dependencies that are not easily reduced to classical Markov structures. In this paper, we explore a theoretically feasible approximation of LLM dynamics using N-order additive Markov chains. Such models allow the conditional probability of the next token to be decomposed into a superposition of contributions from multiple historical depths, reducing the combinatorial explosion typically associated with high-order Markov processes. The main result of the work is the establishment of a correspondence between an additive multi-step chain and a chain with a step-wise memory function. This equivalence allowed the introduction of the concept of information temperature not only for stepwise but also for additive N-order Markov chains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04412 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Additive Multi-Step Markov Chains and the Curse of Dimensionality in Large Language Models Usatenko, O. V. Melnyk, S. S. Pritula, G. M. Computation and Language Large-scale language models (LLMs) operate in extremely high-dimensional state spaces, where both token embeddings and their hidden representations create complex dependencies that are not easily reduced to classical Markov structures. In this paper, we explore a theoretically feasible approximation of LLM dynamics using N-order additive Markov chains. Such models allow the conditional probability of the next token to be decomposed into a superposition of contributions from multiple historical depths, reducing the combinatorial explosion typically associated with high-order Markov processes. The main result of the work is the establishment of a correspondence between an additive multi-step chain and a chain with a step-wise memory function. This equivalence allowed the introduction of the concept of information temperature not only for stepwise but also for additive N-order Markov chains. |
| title | Additive Multi-Step Markov Chains and the Curse of Dimensionality in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.04412 |