Abstract
The rapid advancement of artificial intelligence, particularly large language models, is fundamentally reshaping how we learn and interact with knowledge, offering unprecedented opportunities to develop intelligent systems that enhance human learning at scale. However, realizing this potential requires addressing core technical challenges: optimizing LLMs for pedagogically sound instruction, developing robust computational models to track learners’ misconceptions grounded in counterfactual reasoning, and designing scalable approaches for nuanced, actionable feedback on long free-form student responses. My talk will focus on how my research addresses these challenges by (1) pedagogical alignment of large language models (LLMs), (2) cognitive modeling of student thinking via LLMs trained to reason about students’ counterfactual rationales, and (3) advancing LLM-based grading of very long open-ended responses. By integrating insights from natural language processing and learning sciences, this work aims to create more effective, scalable, and pedagogically grounded LLM-enhanced educational technologies.
For more info, please follow this link.