An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking

TL;DR

This study compares different cognitive forcing functions applied to AI-generated execution plans in writing tasks, finding that assumption analysis most reduces overreliance and enhances critical thinking without increasing cognitive load.

Contribution

It introduces and empirically evaluates four CFF conditions on AI-generated plans, revealing effective strategies to promote critical engagement in AI-assisted workflows.

Findings

Assumption CFF reduces overreliance effectively.

WhatIf CFF is perceived as most helpful by users.

Plan-focused CFFs support critical reflection in GenAI workflows.

Abstract

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.