A study with 24 groups finds LLM intervention explanations in multi-party HRI emphasize facilitation, agreement, and flow, with stable patterns across conditions but role-based differences between mover and opposer robots.
Improving procedural skill explanations via constrained generation: A symbolic-llm hybrid architecture,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Introduces a Pedagogical Model to augment the TMK architecture in Ivy, enabling explicit machine-readable encoding of diagnostic knowledge for learner missteps on course quizzes.
LLM-assisted text-to-model approach generates 23 TMK models from course materials, cutting expert modeling time by 50-70% and supporting scalable procedural skill tutoring.
citing papers explorer
-
Understanding LLM Intervention Explanations in Multi-Party Human-Robot Interaction
A study with 24 groups finds LLM intervention explanations in multi-party HRI emphasize facilitation, agreement, and flow, with stable patterns across conditions but role-based differences between mover and opposer robots.
-
From Explanation to Diagnosis: Next Generation Interactive Video Coach with Misstep Awareness
Introduces a Pedagogical Model to augment the TMK architecture in Ivy, enabling explicit machine-readable encoding of diagnostic knowledge for learner missteps on course quizzes.
-
Developing Models of Procedural Skills using an AI-assisted Text-to-Model Approach
LLM-assisted text-to-model approach generates 23 TMK models from course materials, cutting expert modeling time by 50-70% and supporting scalable procedural skill tutoring.