mlsanityData to 14 Oct 2026

Benchmark of stylistic variation in LLM-generated texts

arXiv 2509.10179 ↗First posted 12 Sep 2025cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

This study investigates the register variation in texts written by humans and comparable texts produced by large language models (LLMs). Biber's multidimensional analysis (MDA) is applied to a sample of human-written texts and AI-created texts generated to be their counterparts to find the dimensions of variation in which LLMs differ most significantly and most systematically from humans. As textual material, a new LLM-generated corpus AI-Brown is used, which is comparable to BE-21 (a Brown family corpus representing contemporary British English). Since all languages except English are underrepresented in the training data of frontier LLMs, similar analysis is replicated on Czech using AI-Koditex corpus and Czech multidimensional model. Examined were 16 frontier models in various settings and prompts, with emphasis placed on the difference between base models and instruction-tuned models. Based on this, a benchmark is created through which models can be compared with each other and ranked in interpretable dimensions.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 13 of its 43 references that are in the map. First posted on arXiv 12 Sep 2025.

Builds on

13 of 43 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  4. 2023Role-Play with Large Language Modelscited by 294
  5. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 229
  6. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  7. 2024The Political Preferences of LLMscited by 84
  8. 2024Do LLMs write like humans? Variation in grammatical and rhetorical stylescited by 62
  9. 2023Stylometric Detection of AI-Generated Text in Twitter Timelinescited by 59
  10. 2024Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?cited by 41
  11. 2024Training on the Benchmark Is Not All You Needcited by 25
  12. 2025Detecting Stylistic Fingerprints of Large Language Modelscited by 11
1 more
  1. 2025Humans can learn to detect AI-generated texts, or at least learn when they can'tcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2025AI Brown and AI Koditex: LLM-Generated Corpora Comparable to Traditional Corpora of English and Czech Textscited by 1
  2. 2026The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Modelscited by 0
  3. 2026How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Frameworkcited by 0
  4. 2026From Context Shift to Stylistic Collapse: Why Training Objectives Matter More Than Scalecited by 0
  5. 2026Production and Perception in LLMs: A Token Probability Approachcited by 0
  6. 2026Optimization Is Not All You Needcited by 0
  7. 2026Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Modelscited by 0