Do Gains from Generative AI-Enabled Adaptive Pretesting Persist? Evidence from a Retention Study

• URL: http://arxiv.org/abs/2606.22328v1
• Date: Sun, 21 Jun 2026 04:34:29 GMT
• Title: Do Gains from Generative AI-Enabled Adaptive Pretesting Persist? Evidence from a Retention Study
• Abstract summary: This study examines the durability of learning gains following GenAI-enabled adaptive pretesting over a seven-week retention period.<n>Findings indicate that adaptive pretesting can elevate initial understanding, but sustained learning depends on how subsequent AI-supported practice is structured.
• Score: 1.1458853556386799
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Transforming GenAI Policy to Prompting Instruction: An RCT of Scalable Prompting Interventions in a CS1 Course [8.222598094097867]
  We conducted a semester-long RCT with four ICAP framework-based instructional conditions varying in engagement intensity with a pre-test, immediate and delayed post-test and surveys.<n>We found that all conditions significantly improved prompting skills, with gains increasing progressively from Condition 1 to Condition 4.<n>For students with similar pre-test scores, higher learning gain in immediate post-test predict higher final exam score, though no direct between-group differences emerged.
  arXiv  Detail & Related papers  (2026-02-17T21:40:12Z)
• Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation [7.755718939237373]
  Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions.<n>We propose a novel method, namely, KDAR, leveraging knowledge distillation to address the prior-dependency dilemmas within the VQA task.<n>Our method achieves state-of-the-art performance on the VQA-CPv2 out-of-distribution (OOD) benchmark.
  arXiv  Detail & Related papers  (2025-01-10T03:42:37Z)
• Analyzing the Impact of AI Tools on Student Study Habits and Academic Performance [0.0]
  The research focuses on how AI tools can support personalized learning, adaptive test adjustments, and provide real-time classroom analysis.<n>Student feedback revealed strong support for these features, and the study found a significant reduction in study hours alongside an increase in GPA.<n>Despite these benefits, challenges such as over-reliance on AI and difficulties in integrating AI with traditional teaching methods were also identified.
  arXiv  Detail & Related papers  (2024-12-03T04:51:57Z)
• Learning Continually by Spectral Regularization [45.55508032009977]
  Continual learning algorithms seek to mitigate loss of plasticity by sustaining good performance while maintaining network trainability. We develop a new technique for improving continual learning inspired by the observation that the singular values of the neural network parameters at initialization are an important factor for trainability during early phases of learning. We present an experimental analysis that shows how the proposed spectral regularizer can sustain trainability and performance across a range of model architectures in continual supervised and reinforcement learning settings.
  arXiv  Detail & Related papers  (2024-06-10T21:34:43Z)
• Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality [55.88910947643436]
  Self-supervised pre-training is essential for handling vast quantities of unlabeled data in practice. HiDe-Prompt is an innovative approach that explicitly optimize the hierarchical components with an ensemble of task-specific prompts and statistics. Our experiments demonstrate the superior performance of HiDe-Prompt and its robustness to pre-training paradigms in continual learning.
  arXiv  Detail & Related papers  (2023-10-11T06:51:46Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• A Survey of the Impact of Self-Supervised Pretraining for Diagnostic Tasks with Radiological Images [71.26717896083433]
  Self-supervised pretraining has been observed to be effective at improving feature representations for transfer learning. This review summarizes recent research into its usage in X-ray, computed tomography, magnetic resonance, and ultrasound imaging.
  arXiv  Detail & Related papers  (2023-09-05T19:45:09Z)
• Meta-Auxiliary Learning for Adaptive Human Pose Prediction [26.877194503491072]
  Predicting high-fidelity future human poses is decisive for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on external datasets and then directly apply it to all test samples, remain non-optimal. We propose a novel test-time adaptation framework that leverages two self-supervised auxiliary tasks to help the primary forecasting network adapt to the test sequence.
  arXiv  Detail & Related papers  (2023-04-13T11:17:09Z)
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [117.72709110877939]
  Test-time adaptation (TTA) has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions.<n>We categorize TTA into several distinct groups based on the form of test data, namely, test-time domain adaptation, test-time batch adaptation, and online test-time adaptation.
  arXiv  Detail & Related papers  (2023-03-27T16:32:21Z)
• Time Series Contrastive Learning with Information-Aware Augmentations [57.45139904366001]
  A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples. How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question. We propose a new contrastive learning approach with information-aware augmentations, InfoTS, that adaptively selects optimal augmentations for time series representation learning.
  arXiv  Detail & Related papers  (2023-03-21T15:02:50Z)
• Persistent Reinforcement Learning via Subgoal Curricula [114.83989499740193]
  Value-accelerated Persistent Reinforcement Learning (VaPRL) generates a curriculum of initial states. VaPRL reduces the interventions required by three orders of magnitude compared to episodic reinforcement learning.
  arXiv  Detail & Related papers  (2021-07-27T16:39:45Z)
• Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates [52.164757178369804]
  Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We conduct an empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework. We also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance.
  arXiv  Detail & Related papers  (2021-01-20T13:59:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.