你能让它听起来像你吗？为个人风格进行后编辑LLM生成文本
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style
AI总结：
研究探讨用户通过后编辑LLM生成文本来塑造个人风格的效果，发现后编辑提高了文本与用户自身写作的相似性，但降低了与LLM生成文本的相似性，同时减少了风格多样性。
摘要：
尽管大型语言模型（LLMs）在写作任务中被广泛应用，但用户在重视个人风格时可能仍不愿依赖LLMs。后编辑LLM生成的草稿或翻译是常见的协作写作策略，但不清楚用户是否能有效重塑LLM生成的文本以反映其个人风格。我们进行了一项预注册的在线研究（n=81），参与者在需要个人风格的写作任务中后编辑LLM生成的草稿。使用基于嵌入的风格相似性度量，我们发现后编辑提高了文本与参与者无协助写作的相似性，并减少了与完全LLM生成输出的相似性。然而，后编辑文本在风格上仍更接近LLM文本而非参与者无协助对照文本，并且其风格多样性低于无协助人类文本。我们发现感知的风格真实性与模型测量的风格相似性之间存在差距，后编辑文本往往被视作代表参与者的个人风格，尽管仍可检测到LLM的风格痕迹。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
