# Small Is Enough: Per-User Style Rewriting of AI-Edited Text via LoRA Adapters

arXiv: https://arxiv.org/abs/2607.29238 · HTML: https://mlsanity.com/paper/2607.29238/

## Key facts

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

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements](https://mlsanity.com/paper/2408.15666/) (2024)
- [TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings](https://mlsanity.com/paper/2406.15586/) (2024)
- [Text Style Transfer Evaluation Using Large Language Models](https://mlsanity.com/paper/2308.13577/) (2023)
- [Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant](https://mlsanity.com/paper/2407.10994/) (2024)
- [AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing](https://mlsanity.com/paper/2603.23069/) (2026)

## Abstract (arXiv)

InMyStyle is a privacy-first, single-user system that adapts small language models to rewrite AI-edited text towards an individual user's writing style without an instruction prompt at inference. Given a user's documents, it uses multiple local helper LLMs to construct paired training examples and fine-tunes LoRA adapters on Qwen2.5 models ranging from 0.5B to 7B parameters. Length-aware generation budgets and automatic chunking support inputs of different lengths. We report a single-user case study: 219 evaluation pairs derived from 73 paragraphs of one author's scientific writing, with all adapters trained using the same rank-8, three-epoch recipe. The automatic composite score (0-1 scale) plateaus across model sizes under both greedy and sampled decoding (Q=0.689-0.695, with overlapping confidence intervals). In this setting, small models are sufficient for the measured rewriting task, and model size mainly determines efficiency trade-offs rather than a stable quality ranking. The gains favor content-preserving naturalization more than recovery of personal style, with authorship probabilities staying near the classifier's decision boundary (0.51--0.53) and stylometric improvement being near zero. As a secondary evaluation, 400 ratings from five LLM judges give InMyStyle outputs a mean perceived AI-ness score over 20% lower than their helper-generated inputs, with scores decreasing with model size in this sample. The study does not establish generalization across users.