# Criticality in Formal Languages and Statistical Physics

arXiv: https://arxiv.org/abs/1606.06737 · HTML: https://mlsanity.com/paper/1606.06737/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2016.

## Built on by (most cited first, 30 of 35)

- [Hyperbolic Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.04562/) (2021)
- [Towards a theory of how the structure of language is acquired by deep neural networks](https://mlsanity.com/paper/2406.00048/) (2024)
- [Deriving Neural Scaling Laws from the statistics of natural language](https://mlsanity.com/paper/2602.07488/) (2026)
- [Tensor networks and efficient descriptions of classical data](https://mlsanity.com/paper/2103.06872/) (2021)
- [Humans and language models diverge when predicting repeating text](https://mlsanity.com/paper/2310.06408/) (2023)
- [Phase transition in large language models and the criticality of natural languages](https://mlsanity.com/paper/2406.05335/) (2024)
- [L2M: Mutual Information Scaling Law for Long-Context Language Modeling](https://mlsanity.com/paper/2503.04725/) (2025)
- [Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay](https://mlsanity.com/paper/2105.05944/) (2021)
- [Explainable Natural Language Processing with Matrix Product States](https://mlsanity.com/paper/2112.08628/) (2021)
- [Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures](https://mlsanity.com/paper/2505.07070/) (2025)
- [Next-token pretraining implies in-context learning](https://mlsanity.com/paper/2505.18373/) (2025)
- [Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision](https://mlsanity.com/paper/2402.12691/) (2024)
- [Do Data-based Curricula Work?](https://mlsanity.com/paper/2112.06510/) (2021)
- [Quantum Algorithms for Compositional Text Processing](https://mlsanity.com/paper/2408.06061/) (2024)
- [States of LLM-generated Texts and Phase Transitions between them](https://mlsanity.com/paper/2503.06330/) (2025)
- [Human-like fleeting memory improves language learning but impairs reading time prediction in transformer language models](https://mlsanity.com/paper/2508.05803/) (2025)
- [Causal Autoregressive Diffusion Language Model](https://mlsanity.com/paper/2601.22031/) (2026)
- [Actionable Entities Recognition Benchmark for Interactive Fiction](https://mlsanity.com/paper/2109.13855/) (2021)
- [Correlation Dimension of Auto-Regressive Large Language Models](https://mlsanity.com/paper/2510.21258/) (2025)
- [Vygotsky Distance: Measure for Benchmark Task Similarity](https://mlsanity.com/paper/2402.14890/) (2024)
- [Rethinking the Relationship between the Power Law and Hierarchical Structures](https://mlsanity.com/paper/2505.04984/) (2025)
- [Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows](https://mlsanity.com/paper/2510.22109/) (2025)
- [Probing How Scalable Table Data Enhances General Long-Context Reasoning](https://mlsanity.com/paper/2603.21719/) (2026)
- [Generative Criticality in Large Language Model Temperature Scaling](https://mlsanity.com/paper/2606.06238/) (2026)
- [On Unsupervised Training of Link Grammar Based Language Models](https://mlsanity.com/paper/2208.13021/) (2022)
- [Long Text Generation Challenge](https://mlsanity.com/paper/2306.02334/) (2023)
- [Strahler Number of Natural Language Sentences in Comparison with Random Trees](https://mlsanity.com/paper/2307.02697/) (2023)
- [Entangling Machine Learning with Quantum Tensor Networks](https://mlsanity.com/paper/2403.12969/) (2024)
- [Overfitting has a limitation: a model-independent generalization gap bound based on R'enyi entropy](https://mlsanity.com/paper/2506.00182/) (2025)
- [SymSeqBench: a unified framework for the generation and analysis of rule-based symbolic sequences and datasets](https://mlsanity.com/paper/2512.24977/) (2025)

## Abstract (arXiv)

We show that the mutual information between two symbols, as a function of the number of symbols between the two, decays exponentially in any probabilistic regular grammar, but can decay like a power law for a context-free grammar. This result about formal languages is closely related to a well-known result in classical statistical mechanics that there are no phase transitions in dimensions fewer than two. It is also related to the emergence of power-law correlations in turbulence and cosmological inflation through recursive generative processes. We elucidate these physics connections and comment on potential applications of our results to machine learning tasks like training artificial recurrent neural networks. Along the way, we introduce a useful quantity which we dub the rational mutual information and discuss generalizations of our claims involving more complicated Bayesian networks.