Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908995423305728 |
|---|---|
| author | Baumler, Connor Bao, Calvin Nghiem, Huy Yang, Xinchen Carpuat, Marine Daumé III, Hal |
| author_facet | Baumler, Connor Bao, Calvin Nghiem, Huy Yang, Xinchen Carpuat, Marine Daumé III, Hal |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24444 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style Baumler, Connor Bao, Calvin Nghiem, Huy Yang, Xinchen Carpuat, Marine Daumé III, Hal Computation and Language 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. |
| title | Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.24444 |