Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Xanthi Kokkinou, Chaido Mizeli, Nafsika Koulaxidou, Marina Delianidi, Konstantinos Diamantaras
• Venue: arXiv: cs.AI
• Published: 2026-07-15
• Collected: 2026-07-16
• URL: http://arxiv.org/abs/2607.14046v1
• PDF: https://arxiv.org/pdf/2607.14046v1
• DOI: 10.26234/heal.ihu.365

Plain-Language Brief

The paper introduces Earthquaker-AI, a hybrid educational framework that combines conversational AI with Lego robotics to teach primary school students about earthquake preparedness. The system uses Lego WeDo2 for simulating seismic response and provides rubric-based feedback for self-regulated learning.

What the Document Says

• The paper presents Earthquaker-AI, a hybrid educational framework that extends the STEM project Earthquaker.
• It uses Lego WeDo2 automation for simulating seismic response and student interaction with sensors and actuators.
• An AI assistant operates as a guided learning mechanism, aligning student responses with safety guidelines and providing rubric-based verbal feedback.
• The system follows a progressive learning trajectory aligned with cognitive development.
• In early grades, the focus is on basic recognition of safety actions through multiple-choice questions.
• In middle grades, students identify correct action sequences through multiple-choice questions.
• In upper grades, the approach shifts to verbal production requiring short written responses.
• The dialogic module uses RAG to match student queries with official guidelines and generate safe, accurate responses.
• Experimental evaluation shows high groundedness and accuracy with a low hallucination rate.

Key Concepts Mentioned

• Earthquake education
• Retrieval-Augmented Generation
• AI assistant
• Lego robotics
• Safety guidelines
• Rubric-based feedback
• Cognitive development
• Self-regulated learning

Claims Made by the Document

• Earthquaker-AI enhances earthquake preparedness and conscious action among primary-school students.
• The system promotes technological literacy, self-regulation, and responsible use of digital systems.

Evidence Used

• Experimental evaluation shows high groundedness and accuracy with a low hallucination rate.

Methods / Approach

• Use of Lego WeDo2 for simulating seismic response
• AI assistant for guided learning and rubric-based feedback

Limitations Stated by the Authors

Unknown

Limitations Noted by the Agent

Agent interpretation — not from the source.

The paper does not discuss potential limitations of the system.

Open Questions

• What are the specific details of the experimental evaluation?
• How was the system implemented in real-world primary school settings?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• The paper mentions an experimental evaluation, but it does not provide specific details about the methodology or results.
• It is unclear how Earthquaker-AI has been used in actual primary school classrooms.

Raw Abstract / Excerpt

This paper presents Earthquaker-AI, a hybrid educational framework building upon a previously implemented educational robotics project by integrating a conversational AI assistant based on Retrieval-Augmented Generation. It aims to enhance earthquake preparedness and conscious action among primary-school students. The system extends the award-winning STEM project Earthquaker moving from mechanical simulation with Lego WeDo2 to cognitive and metacognitive processing. The robotics component uses Lego WeDo2 automation to simulate seismic response, letting students interact with sensors and actuators as tangible representations of protective actions. The assistant operates as a guided learning mechanism aligning student responses with safety guidelines, while providing rubric-based verbal feedback that supports self-regulated learning and calmness under emergency conditions. Earthquaker-AI follows a progressive learning trajectory aligned with cognitive development. In early grades, the focus is on basic recognition of safety actions through multiple-choice questions, assessed via a two-dimensional rubric. In middle grades, students identify correct action sequences through multiple-choice questions, evaluated via a three-axis rubric. In upper grades, the approach shifts to verbal production, requiring short written responses assessed via a four-dimensional rubric that includes clarity of expression. The dialogic module uses RAG to match student queries semantically with official guidelines, generating safe, accurate responses. Experimental evaluation shows high groundedness and accuracy, with a low hallucination rate. Overall, Earthquaker-AI combines hands-on engagement, information processing, and reflective practice. Combining robotics, rubrics, and AI promotes technological literacy, self-regulation, and responsible use of digital systems, contributing to early crisis-management skills.