5 papers · 1 filter
Constructing Evaluation Datasets for Procedural Reasoning: Balancing Naturalness, Grounding, and Multi-Hop Coverage
Sarah Elshabrawy, Rahul K. Dass, Ashok K. Goel
Evaluating procedural reasoning in AI-supported learning systems requires question-answer datasets that are both learner-like and grounded in the instructional knowledge the system…
Improving Procedural Skill Explanations via Constrained Generation: A Symbolic-LLM Hybrid Architecture
Rahul Dass, Thomas Bowlin, Zebing Li +2
In procedural skill learning, instructional explanations must convey not just steps, but the causal, goal-directed, and compositional logic behind them. Large language models (LLMs…
Enhanced Question-Answering for Skill-based learning using Knowledge-based AI and Generative AI
Rahul K. Dass, Rochan H. Madhusudhana, Erin C. Deye +4
Supporting learners' understanding of taught skills in online settings is a longstanding challenge. While exercises and chat-based agents can evaluate understanding in limited cont…
Integrating Cognitive AI with Generative Models for Enhanced Question Answering in Skill-based Learning
Rochan H. Madhusudhana, Rahul K. Dass, Jeanette Luu +1
In online learning, the ability to provide quick and accurate feedback to learners is crucial. In skill-based learning, learners need to understand the underlying concepts and mech…
Combining Cognitive and Generative AI for Self-explanation in Interactive AI Agents
Shalini Sushri, Rahul Dass, Rhea Basappa +2
The Virtual Experimental Research Assistant (VERA) is an inquiry-based learning environment that empowers a learner to build conceptual models of complex ecological systems and exp…