analiza aiqbench
SelfGraphRAG addresses the scarcity of labeled data in graph-based retrieval by synthesizing question-answer pairs directly from knowledge graph structures to train retrievers. This approach effectively leverages relational information for multi-hop reasoning without requiring manual annotation, demonstrating improved precision over standard embedding baselines. The method represents a significant step toward more efficient and scalable RAG systems that fully exploit structured knowledge.
SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation
arXiv:2608.25123v1 Announce Type: cross 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.
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.
16 pages, 2 figures. Based on M.S. thesis work. Thesis available at this https URL. Under review. Code available upon request from manas@umbc.edu
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
H.3.3; I.2.4; I.2.6; I.2.7
arXiv:2608.25123 [cs.CL]
(or arXiv:2608.25123v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.25123 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 256 cuvinte
Subiecte conexe
MoSAIC: Learning DAG Scheduling Heuristics from Optimal Schedules through Motif-Aware Recovery and LLM-Guided Reasoning
arXiv · 14 oct. 2026
Technical Dive into AMD’s MLPerf Training v6.0 Submission
AMD · 16 iun. 2026
Sentence Splitter: Uncovering Latent Factual Structure for Self-Supervised Learning
arXiv · 23 iul. 2026
Mastering Agentic Techniques: AI Agent Customization
NVIDIA · 20 mai 2026