Virginia Tech® home

Seminar: Pedagogy Meets AI: Innovations and Challenges in LLM-Powered Learning

Shashank Sonkar

PhD Candidate
Department of Electrical and Computer Engineering
Rice University

Thursday, February 13
9:30 - 10:30AM
1100 Torgersen Hall

 

Processed With Darkroom

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 AI systems for pedagogically sound instruction, developing robust computational models to track learners' knowledge gaps and misconceptions, and designing scalable approaches for nuanced, actionable feedback. My talk will focus on how my research addresses these challenges by (1) aligning AI tutoring systems with pedagogical principles, (2) developing nuanced LLM-based learner models, and (3) reimagining automated assessment for complex, open-ended responses. By integrating insights from natural language processing and learning sciences, this work aims to create more effective, scalable, and pedagogically grounded AI-enhanced educational technologies.

 

Biography

Shashank Sonkar is a Ph.D. candidate in the Department of Electrical and Computer Engineering at Rice University, advised by Richard Baraniuk, specializing in Natural Language Processing for personalized education. His research focuses on three critical aspects of AI-powered education: pedagogical alignment of large language models, advanced learner modeling, and intelligent assessment. These areas correspond to three key factors that determine educational learning outcomes: instructional approach, learner understanding, and assessment quality. He has collaborated extensively with OpenStax Research, a leading nonprofit organization that develops free, high-quality, openly licensed educational resources, and is a key member of SafeInsights, a large-scale education research hub led by OpenStax at Rice University.