CITATION — REFERENCE ENTRY
exam-harm · bastani-2025-generative-ai-guardrails
- Claim ID
- exam-harm
- Assertion
- In a randomized trial with nearly 1,000 Turkish high school students, access to an unrestricted GPT-4 interface improved practice scores by 48% but reduced scores on a later unassisted exam by 17%; a tutor version with guardrails improved practice scores by 127% and largely eliminated the harm, without producing a positive effect.
- Quote
students in the GPT Base arm perform statistically significantly worse than students in the control arm by 17%; this negative effect is essentially eradicated in the GPT Tutor arm, though we still do not observe a positive effect.
- Quote language
- en
- Locator
- section: Introduction
Available in