# Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style

arXiv: https://arxiv.org/abs/2604.24444 · HTML: https://mlsanity.com/paper/2604.24444/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [Co-Writing with Opinionated Language Models Affects Users' Views](https://mlsanity.com/paper/2302.00560/) (2023)
- [Language Models Learn to Mislead Humans via RLHF](https://mlsanity.com/paper/2409.12822/) (2024)
- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [The Widespread Adoption of Large Language Model-Assisted Writing Across Society](https://mlsanity.com/paper/2502.09747/) (2025)
- [Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits](https://mlsanity.com/paper/2409.14509/) (2024)
- [Detection and Measurement of Syntactic Templates in Generated Text](https://mlsanity.com/paper/2407.00211/) (2024)
- [People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text](https://mlsanity.com/paper/2501.15654/) (2025)
- [StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples](https://mlsanity.com/paper/2410.12757/) (2024)
- [Technical Report on the Pangram AI-Generated Text Classifier](https://mlsanity.com/paper/2402.14873/) (2024)
- [The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers](https://mlsanity.com/paper/2404.02806/) (2024)
- [Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild](https://mlsanity.com/paper/2505.16023/) (2025)
- [Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites](https://mlsanity.com/paper/1908.06809/) (2019)
- [Proxona: Supporting Creators' Sensemaking and Ideation with LLM-Powered Audience Personas](https://mlsanity.com/paper/2408.10937/) (2024)
- [Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process](https://mlsanity.com/paper/2504.12488/) (2025)
- [A SMART Mnemonic Sounds like "Glue Tonic": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick](https://mlsanity.com/paper/2406.15352/) (2024)
- [Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domains](https://mlsanity.com/paper/2509.16531/) (2025)
- [A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users](https://mlsanity.com/paper/2509.18632/) (2025)
- [Style Matters! Investigating Linguistic Style in Online Communities](https://mlsanity.com/paper/2209.13114/) (2022)
- [When Stereotypes GTG: The Impact of Predictive Text Suggestions on Gender Bias in Human-AI Co-Writing](https://mlsanity.com/paper/2409.20390/) (2024)
- [ChatGPT-generated texts show authorship traits that identify them as non-human](https://mlsanity.com/paper/2508.16385/) (2025)

## Built on by (most cited first, 1 of 1)

- [Beating the Style Detector: Three Hours of Agentic Research on the AI-Text Arms Race](https://mlsanity.com/paper/2605.02620/) (2026)

## Abstract (arXiv)

Despite the growing use of large language models (LLMs) for writing tasks, users may hesitate to rely on LLMs when personal style is important. Post-editing LLM-generated drafts or translations is a common collaborative writing strategy, but it remains unclear whether users can effectively reshape LLM-generated text to reflect their personal style. We conduct a pre-registered online study (n=81) in which participants post-edit LLM-generated drafts for writing tasks where personal style matters to them. Using embedding-based style similarity metrics, we find that post-editing increases stylistic similarity to participants' unassisted writing and reduces similarity to fully LLM-generated output. However, post-edited text still remains stylistically closer in style to LLM text than to participants' unassisted control text, and it exhibits reduced stylistic diversity compared to unassisted human text. We find a gap between perceived stylistic authenticity and model-measured stylistic similarity, with post-edited text often perceived as representative of participants' personal style despite remaining detectable LLM stylistic traces.