# Catch Me If You Can? Not Yet: LLMs Still Struggle to Imitate the Implicit Writing Styles of Everyday Authors

arXiv: https://arxiv.org/abs/2509.14543 · HTML: https://mlsanity.com/paper/2509.14543/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 18 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [Contrasting Linguistic Patterns in Human and LLM-Generated News Text](https://mlsanity.com/paper/2308.09067/) (2023)
- [Understanding User Experience in Large Language Model Interactions](https://mlsanity.com/paper/2401.08329/) (2024)
- [Can Large Language Models Identify Authorship?](https://mlsanity.com/paper/2403.08213/) (2024)
- [Towards Optimizing the Costs of LLM Usage](https://mlsanity.com/paper/2402.01742/) (2024)
- [On the State of the Art in Authorship Attribution and Authorship Verification](https://mlsanity.com/paper/2209.06869/) (2022)
- [A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts](https://mlsanity.com/paper/2311.08374/) (2023)
- [LLMs as Writing Assistants: Exploring Perspectives on Sense of Ownership and Reasoning](https://mlsanity.com/paper/2404.00027/) (2024)
- [Exploring the Role of Diversity in Example Selection for In-Context Learning](https://mlsanity.com/paper/2505.01842/) (2025)
- [HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis](https://mlsanity.com/paper/2310.16746/) (2023)
- [CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents](https://mlsanity.com/paper/2405.19778/) (2024)
- [Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning](https://mlsanity.com/paper/2409.04574/) (2024)
- [Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style](https://mlsanity.com/paper/2410.03848/) (2024)
- [Large Language Models can impersonate politicians and other public figures](https://mlsanity.com/paper/2407.12855/) (2024)
- [Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning](https://mlsanity.com/paper/2502.08972/) (2025)
- [Beyond checkmate: exploring the creative chokepoints in AI text](https://mlsanity.com/paper/2501.19301/) (2025)

## Built on by (most cited first, 10 of 10)

- [PersonalBench: Measuring the Authorship Gap in LLM Personalization](https://mlsanity.com/paper/2608.19746/) (2026)
- [Large Language Models and Forensic Linguistics: Navigating Opportunities and Threats in the Age of Generative AI](https://mlsanity.com/paper/2512.06922/) (2025)
- [Authorship Impersonation via LLM Prompting does not Evade Authorship Verification Methods](https://mlsanity.com/paper/2603.29454/) (2026)
- [Theory-Grounded Evaluation Exposes the Authorship Gap in LLM Personalization](https://mlsanity.com/paper/2604.26460/) (2026)
- [The Impact of Editorial Intervention on Detecting Native Language Traces](https://mlsanity.com/paper/2605.10216/) (2026)
- [Interpreting Style Representations via Style-Eliciting Prompts](https://mlsanity.com/paper/2606.05716/) (2026)
- [Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion](https://mlsanity.com/paper/2606.10099/) (2026)
- [AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do Not](https://mlsanity.com/paper/2608.27855/) (2026)
- [When Victorian Becomes a Prompt: Literary Periodization as a Generative Constraint in 100 AI-Generated Novels](https://mlsanity.com/paper/2609.08689/) (2026)
- [Ownership in AI-Assisted Everyday Tasks](https://mlsanity.com/paper/2609.20658/) (2026)

## Abstract (arXiv)

As large language models (LLMs) become increasingly integrated into personal writing tools, a critical question arises: can LLMs faithfully imitate an individual's writing style from just a few examples? Personal style is often subtle and implicit, making it difficult to specify through prompts yet essential for user-aligned generation. This work presents a comprehensive evaluation of state-of-the-art LLMs' ability to mimic personal writing styles via in-context learning from a small number of user-authored samples. We introduce an ensemble of complementary metrics-including authorship attribution, authorship verification, style matching, and AI detection-to robustly assess style imitation. Our evaluation spans over 40000 generations per model across domains such as news, email, forums, and blogs, covering writing samples from more than 400 real-world authors. Results show that while LLMs can approximate user styles in structured formats like news and email, they struggle with nuanced, informal writing in blogs and forums. Further analysis on various prompting strategies such as number of demonstrations reveal key limitations in effective personalization. Our findings highlight a fundamental gap in personalized LLM adaptation and the need for improved techniques to support implicit, style-consistent generation. To aid future research and for reproducibility, we open-source our data and code.