Markovian Generation Chains in Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917333525594112 |
|---|---|
| author | Geng, Mingmeng Mohamed, Amr Shang, Guokan Vazirgiannis, Michalis Poibeau, Thierry |
| author_facet | Geng, Mingmeng Mohamed, Amr Shang, Guokan Vazirgiannis, Michalis Poibeau, Thierry |
| contents | The widespread use of large language models (LLMs) raises an important question: how do texts evolve when they are repeatedly processed by LLMs? In this paper, we define this iterative inference process as Markovian generation chains, where each step takes a specific prompt template and the previous output as input, without including any prior memory. In iterative rephrasing and round-trip translation experiments, the output either converges to a small recurrent set or continues to produce novel sentences over a finite horizon. Through sentence-level Markov chain modeling and analysis of simulated data, we show that iterative process can either increase or reduce sentence diversity depending on factors such as the temperature parameter and the initial input sentence. These results offer valuable insights into the dynamics of iterative LLM inference and their implications for multi-agent LLM systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11228 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Markovian Generation Chains in Large Language Models Geng, Mingmeng Mohamed, Amr Shang, Guokan Vazirgiannis, Michalis Poibeau, Thierry Computation and Language Artificial Intelligence Machine Learning The widespread use of large language models (LLMs) raises an important question: how do texts evolve when they are repeatedly processed by LLMs? In this paper, we define this iterative inference process as Markovian generation chains, where each step takes a specific prompt template and the previous output as input, without including any prior memory. In iterative rephrasing and round-trip translation experiments, the output either converges to a small recurrent set or continues to produce novel sentences over a finite horizon. Through sentence-level Markov chain modeling and analysis of simulated data, we show that iterative process can either increase or reduce sentence diversity depending on factors such as the temperature parameter and the initial input sentence. These results offer valuable insights into the dynamics of iterative LLM inference and their implications for multi-agent LLM systems. |
| title | Markovian Generation Chains in Large Language Models |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.11228 |