← Back to all news
arXiv Machine Learning By Harshdeep Singh, Yurui Zhu, Giovanni Colavizza, Matteo Romanello

Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)

Read the original on arXiv Machine Learning →

The paper introduces EXYGEN, a framework that enables conversational access to large knowledge graphs by combining VoID descriptions, ShEx schemas, retrieved triples, and example question‑query pairs in a retrieval‑augmented generation pipeline. On the SciQA benchmark, this approach achieves an exact‑match score of 0.419 without fine‑tuning any large language model, and shows that larger general‑purpose LLMs can outperform smaller code‑specialized ones when provided sufficient context. To scale metadata generation for very large KGs, the authors propose a predicate‑coverage‑aware parallel graph sampling strategy that preserves structural diversity, reduces runtime by over 80× on OpenCitations Meta and GESIS, and is the only tractable method for obtaining complete metadata on ORKG.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 25

SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions

SPARQL-LLM is an open‑source, triplestore‑agnostic system that generates SPARQL queries from natural language using lightweight metadata and dedicated components for indexing, prompt building, and execution. It achieves up to 59 % higher F1 scores than the next best system on a multilingual challenge and on bioinformatics knowledge graphs, while being up to 27 × faster and costing no more than $0.01 per question. The project is publicly available on GitHub and is already deployed on real‑world decentralized knowledge graphs such as expasy.org/chat.

By Panayiotis Smeros, Vincent Emonet, Ruijie Wang, Ana-Claudia Sima, Tarcisio Mendes de Farias
llmsbenchmarks
More like this →
arXiv Computation and Language
Sep 1

RENSA: Rich Environment Metadata to Navigate Shared and Distributed Endpoints for Automated Federated SPARQL Query Generation

RENSA is a federated SPARQL query generation framework that extends SPARQL Builder Metadata to include class and authority information, enabling precise source selection and semantic constraint inference without runtime ASK queries. The generated metadata profiles occupy less than 1% of the original dataset triples, providing storage‑efficient insights. Evaluation on the LargeRDFBench benchmark shows that RENSA matches state‑of‑the‑art source selection performance while eliminating runtime communication overhead.

By Victor Eiti Yamamoto, Takeda Hideaki, Yamamoto Yasunori
benchmarks
More like this →
arXiv AI
Oct 2

Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying

Build2SPARQL is a large-scale benchmark dataset for translating natural-language questions into SPARQL queries over building knowledge graphs. The dataset is generated by a KG‑grounded pipeline that produces 6,136 executable SPARQL queries and 30,680 corresponding natural-language questions across six query-pattern families and five vocabulary registers, covering 201 building KGs. Human validation shows high semantic fidelity, naturalness, and operational plausibility, and retrieval‑augmented evaluation demonstrates significant accuracy gains for open‑weight language models.

By Wooyoung Jung
llmsragagentsbenchmarks
More like this →