{"version":1,"type":"story","url":"https://digestai.news/story/researchers-release-build2sparql-benchmark-for-text-to-sparql-in-build","json":"https://digestai.news/story/researchers-release-build2sparql-benchmark-for-text-to-sparql-in-build.json","markdown":"https://digestai.news/story/researchers-release-build2sparql-benchmark-for-text-to-sparql-in-build.md","slug":"researchers-release-build2sparql-benchmark-for-text-to-sparql-in-build","headline":"Researchers release Build2SPARQL benchmark for text-to-SPARQL in building KGs","summary":"Researchers introduced **Build2SPARQL**, a new benchmark dataset for converting natural language into SPARQL queries on building knowledge graphs. The dataset includes 6,136 executable SPARQL queries and 30,680 questions derived from 201 building KGs (180 Brick, 21 ASHRAE 223P). The queries cover six pattern families—linear chains, branching, UNION, aggregation, OPTIONAL, and attribute-filtered—phrased across five vocabulary registers.\n\nHuman validation rated 98.8% semantic fidelity and naturalness in 300 sampled questions, with 84% judged operationally plausible. Testing three open-weight language models showed zero-shot accuracy ranged from 0.2% to 20%, but retrieval-augmented prompts improved it to 56–65%. The dataset aims to advance AI-driven query generation for building automation systems.","keyPoints":["Build2SPARQL dataset includes 6,136 SPARQL queries and 30,680 natural-language questions for building KGs","Queries generated via code, questions by LLMs, ensuring correctness independent of model behavior","Three open-weight models achieved 56–65% accuracy with retrieval-augmented prompts, up from 0.2–20% zero-shot"],"whyItMatters":"The dataset accelerates AI research in natural-language querying for building automation, enabling smarter language agents to interact with semantic knowledge graphs. It fills a critical gap in benchmarking for real-world applications like HVAC or energy systems.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":[]},"firstPublishedAt":"2026-10-02T04:00:00Z","updatedAt":"2026-10-02T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying","url":"https://arxiv.org/abs/2610.00224","publishedAt":"2026-10-02T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers release Build2SPARQL benchmark for text-to-SPARQL in building KGs\", 2 October 2026, https://digestai.news/story/researchers-release-build2sparql-benchmark-for-text-to-sparql-in-build","publisher":"Digest AI","title":"Researchers release Build2SPARQL benchmark for text-to-SPARQL in building KGs","datePublished":"2026-10-02T04:00:00Z","url":"https://digestai.news/story/researchers-release-build2sparql-benchmark-for-text-to-sparql-in-build"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}