Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook

arXiv:2509.16780v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise as educational aids but often lack alignment with specific course materials. We investigate Retrieval-Augmented Generation (RAG) and GraphRAG for page-level question answering on an undergraduate mathematics textbook. Using a curated dataset of 477 question-answer pairs, each tied to a specific textbook page, we compare five embedding-based RAG models, a BM25 baseline, and GraphRAG across two metrics: retrieval accuracy (whether the correct page is retrieved) and answer quality (F1 score). Our results show that embedding-based RAG outperforms GraphRAG for page-level retrieval, with voyage-3-large achieving 99.4% accuracy at top-10 (bootstrap 95% CI for top-1: [.644, .728]). BM25 proves a strong baseline, outperforming several embedding models. Error analysis reveals that 63.3% of top-1 failures retrieve same-chapter content, suggesting pedagogical relevance even in failure cases. GraphRAG retrieves excessive context (~47K tokens vs. ~3.7K for RAG), reducing generation quality. We further replicate key experiments using an open-source local LLM (Qwen3.5-35B-A3B), finding that RAG benefits are proportionally larger for weaker models (+39% vs. +16% relative F1 improvement), an important result for cost-sensitive educational deployments. These findings inform the design of AI tutoring systems that reference specific textbook pages.

Abstract:Large language models (LLMs) show promise as educational aids but often lack alignment with specific course materials. We investigate Retrieval-Augmented Generation (RAG) and GraphRAG for page-level question answering on an undergraduate mathematics textbook. Using a curated dataset of 477 question-answer pairs, each tied to a specific textbook page, we compare five embedding-based RAG models, a BM25 baseline, and GraphRAG across two metrics: retrieval accuracy (whether the correct page is retrieved) and answer quality (F1 score). Our results show that embedding-based RAG outperforms GraphRAG for page-level retrieval, with voyage-3-large achieving 99.4% accuracy at top-10 (bootstrap 95% CI for top-1: [.644, .728]). BM25 proves a strong baseline, outperforming several embedding models. Error analysis reveals that 63.3% of top-1 failures retrieve same-chapter content, suggesting pedagogical relevance even in failure cases. GraphRAG retrieves excessive context (~47K tokens vs. ~3.7K for RAG), reducing generation quality. We further replicate key experiments using an open-source local LLM (Qwen3.5-35B-A3B), finding that RAG benefits are proportionally larger for weaker models (+39% vs. +16% relative F1 improvement), an important result for cost-sensitive educational deployments. These findings inform the design of AI tutoring systems that reference specific textbook pages.

Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)

arXiv:2509.16780 [cs.IR]

(or arXiv:2509.16780v3 [cs.IR] for this version)

analiza aiqbench

Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook

Subiecte conexe