用户可修改AI写作以贴近个人风格，但难完全摆脱AI痕迹。
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style
- 让用户编辑AI生成文本，提升其与个人写作风格的相似度。
- 编辑后文本仍比真人写作更像AI，且风格多样性下降。
- 人们误以为修改稿已体现个性，实则仍有明显AI特征。
尽管大型语言模型（LLMs）广泛用于写作任务，但当个人风格重要时，用户仍可能不愿依赖它们。后编辑（post-editing）是常见协作策略，但其能否有效重塑个人风格尚不明确。我们开展了一项预注册在线研究（n=81），让参与者对关乎个人风格的写作任务中由LLM生成的草稿进行后编辑。通过基于嵌入的风格相似性度量发现，后编辑显著提升了文本与用户无辅助写作的风格相似度，降低了与纯LLM输出的相似度。然而，后编辑文本仍比用户无辅助文本更接近于LLM风格，且风格多样性低于真人写作。我们观察到感知的真实性与模型测量的风格相似性之间存在差距：尽管后编辑文本常被用户认为反映个人风格，但仍可检测到明显的LLM风格痕迹。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。