严谨高效！一种可信赖的、由大语言模型驱动的定性数据分析工作流
Efficiency with Rigor! A Trustworthy LLM-powered Workflow for Qualitative Data Analysis
AI总结：
针对大语言模型用于定性数据分析时缺乏可信赖性的问题，提出MindCoder工作流，通过透明性和人类参与策略，实现高效且可信赖的定性数据分析。
摘要：
定性数据分析（QDA）强调可信赖性，需要持续的人类参与和反思。近年来，大语言模型（LLMs）已被应用于定性数据分析以提高效率。然而，其使用引发了关于未经验证的自动化和被取代的意义建构的担忧，这些担忧可能损害可信赖性。为解决这些问题，我们采用了两种策略：透明性和人类参与。通过文献综述和形成性访谈，我们确定了透明自动化和有意义的人类参与的六项设计要求。在这些要求的指导下，我们开发了MindCoder，一种由大语言模型驱动的工作流，它将机械性任务（如分组和验证）委托给系统，同时使人类能够进行有意义的解释。MindCoder还维护用户逐步交互的全面日志，以确保透明性并支持可信赖的结果。在一项涉及12名用户和两名外部评估者的评估中，MindCoder支持主动解释，提供灵活控制，并产生了更可信赖的编码手册。我们进一步讨论了构建人机协作的定性数据分析工作流的设计启示。
英文摘要：
Qualitative data analysis (QDA) emphasizes trustworthiness, requiring sustained human engagement and reflexivity. Recently, large language models (LLMs) have been applied in QDA to improve efficiency. However, their use raises concerns about unvalidated automation and displaced sensemaking, which can undermine trustworthiness. To address these issues, we employed two strategies: transparency and human involvement. Through a literature review and formative interviews, we identified six design requirements for transparent automation and meaningful human involvement. Guided by these requirements, we developed MindCoder, an LLM-powered workflow that delegates mechanical tasks, such as grouping and validation, to the system, while enabling humans to conduct meaningful interpretation. MindCoder also maintains comprehensive logs of users' step-by-step interactions to ensure transparency and support trustworthy results. In an evaluation with 12 users and two external evaluators, MindCoder supported active interpretation, offered flexible control, and produced more trustworthy codebooks. We further discuss design implications for building human-AI collaborative QDA workflows.
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。
