Skip to main content Skip to navigation

DoYouTrustAI: A Tool to Teach Students About AI Misinformation and Prompt Engineering

Project Overview

The document explores the integration of generative AI in education, focusing on the development of 'DoYouTrustAI', a web-based tool aimed at K-12 students. This innovative resource educates students about the risks associated with misinformation generated by AI, particularly Large Language Models (LLMs). By engaging students in evaluating the accuracy of AI-generated summaries about historical figures, the tool fosters critical thinking skills and enhances AI literacy. It underscores the significance of verifying AI outputs and introduces prompt engineering techniques to demonstrate how AI responses can be influenced. The initiative seeks to prepare students to navigate the complexities of AI, ensuring they are equipped to critically assess information and understand the implications of AI technology in their lives. Overall, the findings highlight the potential of generative AI not only as a learning aid but also as a means to cultivate informed and discerning future users of AI systems.

Key Applications

DoYouTrustAI tool

Context: K-12 education, aimed at students in grades K-12

Implementation: Web-based application where students enter a historical figure's name and evaluate AI-generated summaries for accuracy.

Outcomes: Students learn to identify misinformation and understand prompt engineering, improving their critical thinking and AI literacy.

Challenges: Students may struggle to distinguish between accurate and misleading information without external resources.

Implementation Barriers

Educational Barrier

Lack of existing K-12 curriculum focusing on AI misinformation and prompt engineering.

Proposed Solutions: Develop tools like DoYouTrustAI to make these topics approachable and interactive for students.

Project Team

Phillip Driscoll

Researcher

Priyanka Kumar

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Phillip Driscoll, Priyanka Kumar

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies