An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915755368382464 |
|---|---|
| author | Ghosh, Ahana Sarkar, Advait Lindley, Siân Poelitz, Christian |
| author_facet | Ghosh, Ahana Sarkar, Advait Lindley, Siân Poelitz, Christian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18033 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking Ghosh, Ahana Sarkar, Advait Lindley, Siân Poelitz, Christian Human-Computer Interaction Artificial Intelligence 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. |
| title | An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2601.18033 |