# Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study

arXiv: https://arxiv.org/abs/2509.07846 · HTML: https://mlsanity.com/paper/2509.07846/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Convex Optimization: Algorithms and Complexity](https://mlsanity.com/paper/1405.4980/) (2014)
- [Online Learning: A Modern Introduction Using Convex Optimization](https://mlsanity.com/paper/1912.13213/) (2019)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Community Detection and Stochastic Block Models](https://mlsanity.com/paper/1703.10146/) (2017)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [RAG vs. GraphRAG: A Systematic Evaluation and Key Insights](https://mlsanity.com/paper/2502.11371/) (2025)
- [Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference](https://mlsanity.com/paper/2310.03184/) (2023)
- [A Brief Introduction to Machine Learning for Engineers](https://mlsanity.com/paper/1709.02840/) (2017)
- [New Era of Artificial Intelligence in Education: Towards a Sustainable Multifaceted Revolution](https://mlsanity.com/paper/2305.18303/) (2023)
- [System Architecture Optimization Strategies: Dealing with Expensive Hierarchical Problems](https://mlsanity.com/paper/2502.00838/) (2025)
- [Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.05276/) (2025)
- [Foundations of Vector Retrieval](https://mlsanity.com/paper/2401.09350/) (2024)
- [KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?](https://mlsanity.com/paper/2412.08985/) (2024)
- [How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG](https://mlsanity.com/paper/2506.06331/) (2025)

## Built on by (most cited first, 1 of 1)

- [Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing](https://mlsanity.com/paper/2609.25303/) (2026)

## Abstract (arXiv)

Large language models like ChatGPT are increasingly used in classrooms, but they often provide outdated or fabricated information that can mislead students. Retrieval Augmented Generation (RAG) improves reliability of LLMs by grounding responses in external resources. We investigate two accessible RAG paradigms, vector-based retrieval and graph-based retrieval to identify best practices for classroom question answering (QA). Existing comparative studies fail to account for pedagogical factors such as educational disciplines, question types, and practical deployment costs. Using a novel dataset, EduScopeQA, of 3,176 questions across academic subjects, we measure performance on various educational query types, from specific facts to broad thematic discussions. We also evaluate system alignment with a dataset of systematically altered textbooks that contradict the LLM's latent knowledge. We find that OpenAI Vector Search RAG (representing vector-based RAG) performs well as a low-cost generalist, especially for quick fact retrieval. On the other hand, GraphRAG Global excels at providing pedagogically rich answers to thematic queries, and GraphRAG Local achieves the highest accuracy with the dense, altered textbooks when corpus integrity is critical. Accounting for the 10-20x higher resource usage of GraphRAG (representing graph-based RAG), we show that a dynamic branching framework that routes queries to the optimal retrieval method boosts fidelity and efficiency. These insights provide actionable guidelines for educators and system designers to integrate RAG-augmented LLMs into learning environments effectively.