Search and Filter

Do Gains From Generative AI-Enabled Adaptive Pretesting Persist? Evidence From A Retention Study

Date

AI Overview

Why it matters

Immediate access to generative AI can encourage cognitive outsourcing and reduce effortful reasoning. While adaptive pretesting can boost initial learning, it remains unclear whether these learning gains persist over time.

Study at a glance
  • Question: Do learning gains from generative AI adaptive pretesting persist across different types of follow-up practice over seven weeks?
  • Setting and data: Applied statistics course at a public research university in the United States, 89 undergraduate students.
  • Method: Randomized controlled trial (between-subjects experiment with MANCOVA and ANCOVA).
Key findings
  • Adaptive spaced retrieval practice led to significantly higher posttest retention scores (78.19) than learner-directed AI study (67.28).
  • Both adaptive and fixed retrieval practice elicited significantly higher observed practice effort from undergraduates than learner-directed AI study.
  • Scores and observed practice effort did not differ significantly between adaptive and fixed spaced retrieval practice groups.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

Pretesting - attempting problems before instruction - supports learning by activating prior knowledge and sharpening attention to subsequent instruction. Recent work suggests that adaptive AI-assisted pretesting can yield further advantages, particularly for tasks requiring higher-order reasoning, yet it remains unclear whether these gains persist over time. This study examines the durability of learning gains following GenAI-enabled adaptive pretesting over a seven-week retention period. Undergraduate participants completed an adaptive AI-assisted pretesting session, received instruction, and took a baseline assessment, then were randomly assigned to adaptive spaced retrieval practice, fixed spaced retrieval practice, or learner-directed AI-supported study. Multivariate analyses revealed a significant effect of condition on posttest performance and observed practice effort, with retrieval-based conditions outperforming learner-directed study. Findings indicate that adaptive pretesting can elevate initial understanding, but sustained learning depends on how subsequent AI-supported practice is structured.

Research Categories

What is the application?
Who is the user?
Who age?

Publication Source

Publisher
arXiv