Research map / Large language models / AI and society

Understanding GenAI for Teaching and Learning in Secondary Classrooms

AAAI 2025 · Large language models › AI and society · approach: Classroom tools and student perceptions · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

A doctoral consortium proposal describing workshops and teacher co-design studies on GenAI for secondary classrooms, and a planned RAG-based student chatbot evaluated in a quasi-experimental study.

Problem

Little work has examined how LLMs and GenAI can benefit secondary (K-12) education, incorporating instructor design insights and measuring effects on student learning outcomes.

Approach

Ground the design of a classroom chatbot in secondary teachers' own design input gathered through GenAI workshops and co-design sessions, then build a RAG-based student chatbot informed by that input and evaluate it in a quasi-experimental classroom study.

Key results

• Preliminary results (as stated) suggest secondary teachers would prefer a tailored GenAI agent in their classroom over simply using ChatGPT or an equivalent system.
• Study 1 (P1) data collection with a new teacher cohort is complete and analysis is in progress; the workshop series in Reichert et al. was the first free, publicly available, research-vetted course for secondary teachers on LLMs and GenAI.
• Study 2 (P2) is planned as a quasi-experimental evaluation of a RAG-based chatbot with secondary students, using pre- and post-tests and Likert surveys.

Limitations

• The RAG chatbot has not yet been built or evaluated; the work is a proposal with planned studies.
• Teacher design findings are preliminary and analysis is ongoing.
• Evaluation is planned in a quasi-experimental setup with limited sections and students.

Experimental setup

Metrics: Likert-scale survey responses pre- and post-test learning outcomes (planned) thematic analysis descriptive statistics

Baselines: ChatGPT

Builds on: retrieval-augmented generation

Closest papers by meaning

• Design and Evaluation of a Generative Artificial Intelligence-Based Tool for Students with Learning Disabilities in Kenya (AAAI 2025 · similarity 0.87)
• Students’ Perceptions and Preferences of Generative Artificial Intelligence Feedback for Programming (AAAI 2024 · similarity 0.86)
• MerryQuery: A Trustworthy LLM-Powered Tool Providing Personalized Support for Educators and Students (AAAI 2025 · similarity 0.85)
• From Consumers to Critical Users: Prompty, an AI Literacy Tool for High School Students (AAAI 2024 · similarity 0.85)
• LLMs in the Classroom: Outcomes and Perceptions of Questions Written with the Aid of AI (AAAI 2025 · similarity 0.85)
• Word2Vec4Kids: Interactive Challenges to Introduce Middle School Students to Word Embeddings (AAAI 2025 · similarity 0.83)