# Privacy Personalization Trade offs in LLMs: The Impact of Stylometric Signal Reduction on User-Specific Text Generation

arXiv: https://arxiv.org/abs/2609.22112 · HTML: https://mlsanity.com/paper/2609.22112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 15 of 15)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Benchmarking Cognitive Biases in Large Language Models as Evaluators](https://mlsanity.com/paper/2309.17012/) (2023)
- [Can LLM be a Personalized Judge?](https://mlsanity.com/paper/2406.11657/) (2024)
- [Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation](https://mlsanity.com/paper/2404.05970/) (2024)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [The Topic Confusion Task: A Novel Scenario for Authorship Attribution](https://mlsanity.com/paper/2104.08530/) (2021)
- [PART: Pre-trained Authorship Representation Transformer](https://mlsanity.com/paper/2209.15373/) (2022)
- [DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts](https://mlsanity.com/paper/2408.08930/) (2024)
- [Automated Profile Inference with Language Model Agents](https://mlsanity.com/paper/2505.12402/) (2025)
- [Forensic Authorship Analysis of Microblogging Texts Using N-Grams and Stylometric Features](https://mlsanity.com/paper/2003.11545/) (2020)
- [De-Anonymization at Scale via Tournament-Style Attribution](https://mlsanity.com/paper/2601.12407/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated the ability to generate user-specific text with high stylistic fidelity. However, the personal data that enables such personalization frequently embeds demographic, cultural, and stylistic markers that raises concerns about stylometric re- identification. This paper investigates whether reducing identifiable stylistic signals affects personalization in text generation by LLMs. We introduce a controlled framework to isolate stylometric signals in LLM personalization using the LaMP-7 Twitter benchmark. Experiments on 250 sampled users compare two settings: paraphrasing conditioned on the original profile and paraphrasing conditioned on an anonymized converted profile in which demographic identifiers, cultural references, personal details, and informal linguistic cues have been systematically neutralized. Outputs are assessed by two independent LLM judges and a complementary human evaluation. Our pairwise evaluation shows that outputs conditioned on original profiles are nearly indistinguishable from human-authored ground truth, indicating that modern LLMs can closely reproduce an author's writing style with sufficient fidelity. In contrast, preference for model outputs with anonymized profiles drops to 13.0% on average, while semantic context preservation remains high at 94.8%. A study with human evaluators confirms the same pattern. These findings reveal a clear privacy-personalization trade-off and highlight the need for privacy-aware personalization methods that retain meaning while suppressing identifying stylistic signals.