为视觉-语言-动作模型的教育对齐：一个全面的框架，用于数据、架构和教育中的评估
Pedagogical Alignment for Vision-Language-Action Models: A Comprehensive Framework for Data, Architecture, and Evaluation in Education
AI总结：
本文提出教育VLA框架，通过四个组件实现轻量级模型的教育对齐，提升科学教育中的任务表现和解释生成能力。
摘要：
科学演示对于有效的STEM教育至关重要，但教师在安全且一致地多次进行演示时面临挑战，其中机器人可以有所帮助。然而，当前的视觉-语言-动作（VLA）模型需要大量的计算资源，并牺牲语言生成能力以最大化效率，使其不适合资源受限的教育环境，这些环境需要可解释的、能生成解释的系统。我们提出了\textit{教育VLA框架}，通过四个组件对轻量级VLA模型应用教育对齐：文本修复以恢复语言生成能力，大规模语言模型（LLM）蒸馏以转移教育知识，安全训练用于教育环境，以及调整到科学教育情境的教育评估。我们评估了教育VLA框架在五个科学演示中的表现，涵盖物理、化学、生物和地球科学，使用与科学教育专家合作开发的评估框架。我们的评估通过教师调查和LLM-as-Judge评估评估了任务表现（成功率、协议合规性、效率、安全性）和教育质量。我们还提供了生成文本的定性分析。实验结果表明，教育VLA框架在任务表现上与基线模型相当，同时生成上下文合适的教育解释。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
