用思维强制机制提升写作中对AI计划的批判性思考
An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking
- 设计三种强制机制，要求用户分析假设或测试反事实
- 假设型机制最有效降低依赖，且不增加负担
- 适合关注AI辅助写作中反思能力的研究者
生成式AI工具在写作等知识工作流程中提升效率，但也带来过度依赖和批判性思维减弱的风险。认知强制机制（CFFs）通过要求用户主动参与AI输出来缓解这些风险。随着AI工作流日益复杂，系统越来越多地呈现需用户审查的执行计划，但这些计划本身由AI生成，同样存在过度依赖问题。本研究开展控制实验，参与者在完成AI辅助写作任务时，在四种CFF条件下审查由AI生成的计划：假设分析、反事实测试、两者结合，以及无强制的对照组。后续的思考录音与访谈研究进一步对比了各条件。结果表明，假设型CFF最有效减少过度依赖，且未增加认知负荷；而反事实型被感知为最有帮助。研究凸显了针对执行计划的CFF在支持生成式AI辅助知识工作中进行批判性反思的价值。
原文摘要 · Abstract (English)
Generative AI (GenAI) tools improve productivity in knowledge workflows such as writing, but also risk overreliance and reduced critical thinking. Cognitive forcing functions (CFFs) mitigate these risks by requiring active engagement with AI output. As GenAI workflows grow more complex, systems increasingly present execution plans for user review. However, these plans are themselves AI-generated and prone to overreliance, and the effectiveness of applying CFFs to AI plans remains underexplored. We conduct a controlled experiment in which participants completed AI-assisted writing tasks while reviewing AI-generated plans under four CFF conditions: Assumption (argument analysis), WhatIf (hypothesis testing), Both, and a no-CFF control. A follow-up think-aloud and interview study qualitatively compared these conditions. Results show that the Assumption CFF most effectively reduced overreliance without increasing cognitive load, while participants perceived the WhatIf CFF as most helpful. These findings highlight the value of plan-focused CFFs for supporting critical reflection in GenAI-assisted knowledge work.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。