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

arXiv:2607.29238 · cs.CL, cs.AI, cs.CY, cs.ET, cs.HC · Submitted 2026-07-31 · Read on arXiv

cs.CL, cs.AI, cs.CY, cs.ET, cs.HC

Submitted: 2026-07-31

Updated: 2026-09-25

Code: https://github.com/achak1987/inmystyle

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• LoRA Adapters — 7× in this paper · explained in 3 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• QLoRA — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• LLM-as-a-Judge — 3× in this paper · explained in 4 episodes
• Calibration — 2× in this paper · explained in 9 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• LoRA Adaptation — 2× in this paper · explained in 2 episodes
• Obfuscation — 2× in this paper · explained in 2 episodes
• Papers — 2× in this paper · explained in 3 episodes
• Personalization — 2× in this paper · explained in 2 episodes
• Quantization — 2× in this paper · explained in 15 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Composition — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 14 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 5 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes
• Weight Decay — 1× in this paper · explained in 2 episodes

Sources

• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• QLoRA: Efficient Finetuning of Quantized LLMs
• RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors
• StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
• The Llama 3 Herd of Models
• The Curious Case of Neural Text Degeneration
• TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
• LoRA: Low-Rank Adaptation of Large Language Models
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
• Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant
• Qwen2.5 Technical Report
• Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning
• BERTScore: Evaluating Text Generation with BERT

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering