Research map / Large language models / AI and society
MerryQuery: A Trustworthy LLM-Powered Tool Providing Personalized Support for Educators and Students
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.
Presents MerryQuery, a RAG-based course-specific educational assistant built on GPT-4o that offers source citation, guided practice/review modes, instructor monitoring, and multimodal PDF processing.
Problem
LLMs in education raise concerns about academic misconduct, misinformation, and student overreliance, which limit their adoption by educators and students.
Approach
A trustworthy educational assistant combining RAG over course materials, source citations, instructor-controlled granularity (practice vs. review modes) enforced via prompt engineering and pre/post-generation rules, and instructor access to chat logs and usage statistics.
Key results
- Initial results reported as qualitative only: the system performs effectively in providing accurate, course-specific assistance, with minor refinements remaining.
- Multimodal pipeline combines PDF repair, text mining, and multi-step OCR (binarization, morphological transforms, Tesseract) embedded into a vector database for RAG retrieval.
Limitations
- No quantitative evaluation of accuracy, learning outcomes, or trust; results are qualitative initial observations
- Depends on a closed API (OpenAI GPT-4o) and the system is stateless-API dependent requiring a custom memory mechanism
- Several features (automated grading, RLHF, personalized strategy generation) are still under development
Experimental setup
Datasets: course materials uploaded by instructors (e.g., syllabus, PDFs with text, tables, images)
Baselines: ChatGPT
Builds on: Retrieval-Augmented Generation
Closest papers by meaning
- Developing LLM-Powered Trustworthy Agents for Personalized Learning Support (AAAI 2025 · similarity 0.92)
- LLMs in the Classroom: Outcomes and Perceptions of Questions Written with the Aid of AI (AAAI 2025 · similarity 0.87)
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection (ICLR 2024 · similarity 0.86)
- Boosting the Potential of Large Language Models with an Intelligent Information Assistant (NeurIPS 2024 · similarity 0.86)
- Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG (ICLR 2025 · similarity 0.86)
- RetLLM-E: Retrieval-Prompt Strategy for Question-Answering on Student Discussion Forums (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.