Back to AI News
arxiv

GenSPARQL: A Generative Extension of SPARQL for Incomplete Knowledge Graphs

GenSPARQL extends SPARQL 1.1 with a GENOP operator that binds LLM-generated values to query variables during query evaluation. A similarity join maps generated names to entity IRIs, and the query planner invokes the LLM only for bindings selected by other graph patterns and filters. Evaluation with three open-weight LLMs shows the embedding similarity maps 83% of entities named by the LLMs and yields only one incorrect match. A web workbench lets attendees query two Wikidata-derived graphs and inspect generated values, mapped entities, and LLM calls.

AI Brief

It provides a concrete, evaluated method for combining LLM-generated facts with structured knowledge graph queries, useful for researchers and builders dealing with incomplete data.

arXiv:2611.26062v1 Announce Type: cross Abstract: Knowledge graphs on the Web are incomplete, and SPARQL answers a query only from the stored triples. Large language models (LLMs) can predict missing facts, but an LLM returns names instead of IRIs and requires one call per binding of a query variable. We present GenSPARQL, a generative extension of SPARQL 1.1 with an operator GENOP that binds values generated by an LLM to query variables during query evaluation. A similarity join maps generated names to entities of the graph, and the query planner invokes the LLM only for the bindings selected by the other graph patterns and filters. In a web workbench, attendees query two graphs built from Wikidata and inspect generated values, mapped entities and LLM calls. In our evaluation with three open-weight LLMs, the embedding similarity maps 83% of the entities named by the LLMs and yields only one incorrect match.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!