arXiv:2606.27742v1 Announce Type: cross Abstract: Enterprise Knowledge Graphs (KGs) are increasingly used for internal search, analytics, and question answering, but building natural-language interfaces for private enterprise graphs remains costly. We present KG2Cypher, a data-centric pipeline for building enterprise text-to-Cypher systems from existing KGs. KG2Cypher first constructs an executable Cypher query from observed graph facts and then uses LLMs to generate its associated natural-language question. The resulting Text-Cypher pairs are validated with an LLM judge and human validation,
The proliferation of LLMs and enterprise knowledge graphs is creating an urgent need for more accessible and automated ways to query complex internal data.
This development allows enterprises to unlock deeper insights from their internal knowledge graphs by enabling natural language querying, greatly enhancing data accessibility for non-technical users.
The ability to automatically generate and validate text-to-Cypher systems dramatically reduces the cost and technical barrier for enterprises to implement sophisticated natural language interfaces for their KGs.
- · Enterprise software providers
- · LLM developers
- · Data scientists and analysts
- · Companies with large, untapped knowledge graphs
- · Manual Cypher query developers
- · Traditional BI tools with rigid interfaces
Enterprises can more easily deploy natural language interfaces for internal data, increasing data democratization.
Improved access to enterprise knowledge graphs will accelerate internal innovation and decision-making by surfacing hidden connections and insights.
The development of robust and validated text-to-Cypher systems could lead to more sophisticated autonomous agents operating directly on enterprise data environments.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI