An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking
This addresses the problem of overreliance on AI in knowledge work for users, but it is incremental as it builds on existing CFF research by applying it to AI plans.
The study investigated how cognitive forcing functions (CFFs) applied to AI-generated execution plans affect overreliance and critical thinking in AI-assisted writing, finding that the Assumption CFF most effectively reduced overreliance without increasing cognitive load, while participants perceived the WhatIf CFF as most helpful.
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.