Publications by authors named "Blair Lehman"
Article Synopsis
- Large language models (LLMs) are being increasingly utilized in education to create personalized learning experiences that cater to the whole learner, considering both cognitive and non-cognitive traits.
- The article identifies three major challenges to achieving this personalized approach: improving how LLMs represent learners, developing adaptive technologies for tailored support, and effectively creating and evaluating educational agents powered by LLMs.
- To tackle these challenges, the authors discuss methods for interpreting LLM behaviors, utilizing feedback and support strategies, and the complexities of using natural language for designing educational agents.
In line with the positive effects of personalized learning, personalized assessments are expected to maximize learner motivation and engagement, allowing learners to show what they truly know and can do. Considering the advances in Generative Artificial Intelligence (GenAI), in this perspective article, we elaborate on the opportunities of integrating GenAI into personalized educational assessments to maximize learner engagement, performance, and access. We also draw attention to the challenges of integrating GenAI into personalized educational assessments regarding its potential risks to the assessment's core values of validity, reliability, and fairness.
View Article and Find Full Text PDF