SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation

arXiv:2608.25123 · cs.CL, cs.AI · Submitted 2026-08-25 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-08-25

Updated: 2026-08-25

Comments: 16 pages, 2 figures. Based on M.S. thesis work. Thesis available at https://www.proquest.com/docview/3350071346. Under review. Code available upon request from manas@umbc.edu

License: http://creativecommons.org/licenses/by/4.0/

The gist: Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often underuse the relational structure encoded in

Terminology

Abstract

Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often underuse the relational structure encoded in knowledge graphs. Graph-based RAG can capture entity relationships, yet supervised graph retrieval typically requires labeled question-answer data that may not be available for newly constructed graphs. We address this limitation with SelfGraphRAG, a framework that generates question-answer pairs directly from knowledge graph structure and uses them to train a query-conditioned graph retriever. The generated questions capture multi-hop paths and local neighborhoods, providing relational supervision without manual annotation. Experiments on multi-hop question answering and classification benchmarks show that SelfGraphRAG improves retrieval precision and downstream reasoning performance over embedding-based baselines. These results suggest that knowledge graph structure can provide useful supervision for training graph retrievers when labeled data are unavailable.

Sources

Related papers