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.

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