# Scale-free Characteristics of Multilingual Legal Texts and the Limitations of LLMs

arXiv: https://arxiv.org/abs/2509.17367 · HTML: https://mlsanity.com/paper/2509.17367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 10 of 10)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer](https://mlsanity.com/paper/2109.00904/) (2021)
- [A standardized Project Gutenberg corpus for statistical analysis of natural language and quantitative linguistics](https://mlsanity.com/paper/1812.08092/) (2018)
- [MultiLegalPile: A 689GB Multilingual Legal Corpus](https://mlsanity.com/paper/2306.02069/) (2023)
- [Applicability of Large Language Models and Generative Models for Legal Case Judgement Summarization](https://mlsanity.com/paper/2407.12848/) (2024)
- [Evaluating Computational Language Models with Scaling Properties of Natural Language](https://mlsanity.com/paper/1906.09379/) (2019)
- [Taylor's law for Human Linguistic Sequences](https://mlsanity.com/paper/1804.07893/) (2018)

## Abstract (arXiv)

We present a comparative analysis of text complexity across domains using scale-free metrics. We quantify linguistic complexity via Heaps' exponent β (vocabulary growth), Taylor's exponent α (word-frequency fluctuation scaling), compression rate r (redundancy), and entropy. Our corpora span three domains: legal documents (statutes, cases, deeds) as a specialized domain, general natural language texts (literature, Wikipedia), and AI-generated (GPT) text. We find that legal texts exhibit slower vocabulary growth (lower β) and higher term consistency (higher α) than general texts. Within legal domain, statutory codes have the lowest β and highest α, reflecting strict drafting conventions, while cases and deeds show higher β and lower α. In contrast, GPT-generated text shows the statistics more aligning with general language patterns. These results demonstrate that legal texts exhibit domain-specific structures and complexities, which current generative models do not fully replicate.