AuthScribe:在大语言模型辅助的反思式日志撰写中支持自主性与作者身份
AuthScribe: Supporting Agency and Authorship in LLM-Assisted Reflective Journaling
AI总结:
该研究针对大语言模型辅助反思式日志撰写中作者身份与自主性的问题,提出AuthScribe系统,经14天实地测试,发现其可帮助参与者建立经历与过往解读的联系,为相关AI系统设计提供启示。
摘要:
大型语言模型正越来越多地被用于反思式日志撰写,在这类场景中,清晰表达自身经历是解读经历的一部分。这引发了关于撰写者如何保留作者身份、行使自主性以及评估个性化辅助的问题。我们提出了AuthScribe,这是一个大语言模型辅助的反思式日志撰写系统,它结合了上下文锚点、撰写者控制的AI支持、自传式引用以及只读的临时草稿,要求在AI生成的建议进入日志前需重新表达。检索和大语言模型推理在设备端运行。在为期14天、有14名参与者的实地部署中,(参与者的)立足点从定位当前经历转变为将其与先前自我撰写的解读重新建立联系。感知到的自主性在第1周保持稳定,在第2周发生转变。参与者通过将AI生成的建议转化为具有个人意义的表达来描述作者身份,并在能够追溯到先前写作时信任个性化提示。我们讨论了AI系统用于个人反思时在采用阻力、纵向自主性和可追溯个性化方面的设计启示。
英文摘要:
Large language models are increasingly used in reflective journaling, where articulating an experience is part of interpreting it. This raises questions about how writers retain authorship, exercise agency, and assess personalized assistance. We present AuthScribe, an LLM-assisted reflective journaling system that combines contextual anchors, writer-steered AI support, Autobiographical Citations, and read-only Provisional Drafts that require re-expression before AI-generated suggestions enter the journal. Retrieval and LLM inference run on-device. In a 14-day field deployment with 14 participants, grounding shifted from situating current experiences to reconnecting them with prior self-authored interpretations. Perceived agency remained stable through Week 1 and shifted during Week 2. Participants described authorship through transforming AI-generated suggestions into personally meaningful expression, and trusted personalized prompts when they could trace them to prior writing. We discuss design implications for adoption friction, longitudinal agency, and traceable personalization in AI systems for personal reflection.
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。