arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.05819cs.HC
收藏

作者漂移:在LLM辅助写作中自我效能与信任如何演变

Authorship Drift: How Self-Efficacy and Trust Evolve During LLM-Assisted Writing

School of Computing KAIST(KAIST计算学院);SkillBench

Yeon Su Park, Nadia Azzahra Putri Arvi, Seoyoung Kim, Juho Kim

AI总结:

研究探讨了在LLM辅助写作中,自我效能和信任如何演变,并提出了支持人类与LLM协作中作者身份的设计建议。

摘要:

大型语言模型(LLMs)越来越多地被用作写作中的协作伙伴。然而,这提出了一个关键的作者身份问题,因为用户和模型在交互回合中共同塑造文本。理解这种背景下作者身份需要考察用户在协作中的演变内部状态,特别是自我效能和信任。然而,这些状态的动力学及其与用户提示策略和作者身份结果之间的关联仍鲜为人知。我们通过研究302名参与LLM辅助写作的参与者,捕捉交互日志和每回合的自我效能和信任评分,探讨了这些动态。我们的分析显示,协作通常会降低用户的自我效能,同时增加信任。失去自我效能的参与者更可能要求LLM直接编辑他们的作品,而恢复自我效能的参与者则要求更多的审查和反馈。此外,自我效能稳定的参与者在最终文本的实际和感知作者身份上表现更高。基于这些发现,我们提出了关于理解和支持人类-LLM协作中作者身份的设计建议。

英文摘要:

Large language models (LLMs) are increasingly used as collaborative partners in writing. However, this raises a critical challenge of authorship, as users and models jointly shape text across interaction turns. Understanding authorship in this context requires examining users' evolving internal states during collaboration, particularly self-efficacy and trust. Yet, the dynamics of these states and their associations with users' prompting strategies and authorship outcomes remain underexplored. We examined these dynamics through a study of 302 participants in LLM-assisted writing, capturing interaction logs and turn-by-turn self-efficacy and trust ratings. Our analysis showed that collaboration generally decreased users' self-efficacy while increasing trust. Participants who lost self-efficacy were more likely to ask the LLM to edit their work directly, whereas those who recovered self-efficacy requested more review and feedback. Furthermore, participants with stable self-efficacy showed higher actual and perceived authorship of the final text. Based on these findings, we propose design implications for understanding and supporting authorship in human-LLM collaboration.

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。

↑