观察生成式人工智能支持下的系统综述实施：来自软件工程研究生课程的经验报告
Observing the Conduct of Systematic Reviews with Generative AI Support: An Experience Report from a Graduate Software Engineering Course
浏览论文内容
中文总结 AI 辅助
本研究通过观察十名博士生在有或无生成式AI支持下开展系统综述的课堂活动，发现AI能降低门槛并暴露方法问题，但需人工监督与批判反思，为后续对照研究提供设计依据。
中文摘要 AI 辅助
背景：二次研究是循证软件工程中的基本实践，但教授这些实践需要让学生接触真实方法论决策的活动。目标：本文报告了一门研究生课程中的经验，在该课程中，十名软件工程博士生分为三组，在有和没有生成式人工智能支持的情况下试点进行了二次研究。方法：组织并观察了一次为期一天的课堂活动，各组在有和没有生成式人工智能支持的情况下进行了试点系统综述。对课堂观察、产生的工件以及与配置在ChatGPT中的助手的交互线程进行了分析，以重建每个小组在整个活动中如何利用该技术。结果：大语言模型降低了初始障碍，加速了备选方案的生成，并使方法论问题更加明确，但也助长了过度委托、表面验证、操作困难以及关注点从实施系统综述转向使用工具的问题。结论：该经验提供了博士生在系统综述活动中如何参与生成式人工智能的情境化观察记录，所得见解也为后续对照研究的设计提供了信息。研究结果表明，生成式人工智能可以支持关于系统综述的实践学习，前提是将其使用与人工监督、决策记录和对局限性的批判性反思相结合。
英文摘要
Context: Secondary studies are fundamental practices in Evidence- Based Software Engineering, but teaching them requires activities that expose students to authentic methodological decisions. Objective: This paper reports an experience in a graduate course in which ten doctoral students in Software Engineering, organized into three groups, piloted secondary studies with and without support from generative AI. Method: A single-day classroom session was organized and observed, in which the groups conducted pilot systematic reviews with and without generative AI support. Classroom observations, produced artifacts, and interaction threads with assistants configured in ChatGPT were analyzed to reconstruct how each group appropriated the technology throughout the activity. Results: LLMs reduced initial barriers, accelerated the generation of alternatives, and made methodological problems more explicit, but they also favored excessive delegation, superficial validation, operational difficulties, and a shift in focus from conducting the SLR to using the tool. Conclusion: The experience offers a situated, observational account of how doctoral students engaged with generative AI during a systematic review activity, and the resulting insights also inform the design of a subsequent controlled study. The findings indicate that generative AI can support practical learning about SLRs, provided that its use is accompanied by human supervision, decision records, and critical reflection on its limitations.
发表机构
- Cesar School（塞萨尔学院）
机构由 AI 辅助整理，请以论文原文为准。
