Pedagogical Alignment for Vision-Language-Action Models: A Comprehensive Framework for Data, Architecture, and Evaluation in Education

TL;DR

This paper introduces a Pedagogical VLA Framework that adapts lightweight vision-language-action models for science education, enhancing safety, pedagogical quality, and explanation generation in resource-constrained settings.

Contribution

It proposes a comprehensive framework combining text healing, LLM distillation, safety training, and pedagogical evaluation to improve VLA models for educational use.

Findings

Achieves comparable task performance to baseline models

Produces contextually appropriate educational explanations

Enhances safety and pedagogical quality in science demonstrations

Abstract

Science demonstrations are important for effective STEM education, yet teachers face challenges in conducting them safely and consistently across multiple occasions, where robotics can be helpful. However, current Vision-Language-Action (VLA) models require substantial computational resources and sacrifice language generation capabilities to maximize efficiency, making them unsuitable for resource-constrained educational settings that require interpretable, explanation-generating systems. We present \textit{Pedagogical VLA Framework}, a framework that applies pedagogical alignment to lightweight VLA models through four components: text healing to restore language generation capabilities, large language model (LLM) distillation to transfer pedagogical knowledge, safety training for educational environments, and pedagogical evaluation adjusted to science education contexts. We evaluate Pedagogical VLA Framework across five science demonstrations spanning physics, chemistry, biology, and earth science, using an evaluation framework developed in collaboration with science education experts. Our evaluation assesses both task performance (success rate, protocol compliance, efficiency, safety) and pedagogical quality through teacher surveys and LLM-as-Judge assessment. We additionally provide qualitative analysis of generated texts. Experimental results demonstrate that Pedagogical VLA Framework achieves comparable task performance to baseline models while producing contextually appropriate educational explanations.