{"ID":2835245,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00590","arxiv_id":"2512.00590","title":"Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models","abstract":"Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain text by extracting candidate triplets with qualifiers, enforcing Wikidata-based type and relation constraints, and normalizing entities to reduce duplication. The resulting KGs are compact, ontology-consistent, and well-connected; on MuSiQue, the correct answer entity appears in 96% of generated triplets. On HotpotQA, our triplets-only setup achieves 76.0 F1, and on MuSiQue 59.8 F1, matching or surpassing several retrieval-augmented generation baselines that still require textual context. In addition, Wikontic attains state-of-the-art information-retention performance on the MINE-1 benchmark (86%), outperforming prior KG construction methods. Wikontic is also efficient at build time: KG construction uses less than 1,000 output tokens, about 3$\\times$ fewer than AriGraph and $\u003c$1/20 of GraphRAG. The proposed pipeline enhances the quality of the generated KG and offers a scalable solution for leveraging structured knowledge in LLMs.","short_abstract":"Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from o...","url_abs":"https://arxiv.org/abs/2512.00590","url_pdf":"https://arxiv.org/pdf/2512.00590v2","authors":"[\"Alla Chepurova\",\"Aydar Bulatov\",\"Mikhail Burtsev\",\"Yuri Kuratov\"]","published":"2025-11-29T18:44:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}