Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Loconte, Lorenzo, Hospedales, Timothy, Cornelio, Cristina
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911726149042176
author Loconte, Lorenzo
Hospedales, Timothy
Cornelio, Cristina
author_facet Loconte, Lorenzo
Hospedales, Timothy
Cornelio, Cristina
contents Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic operations like aggregation or exhaustive listing. Retrieval-augmented generation has become the dominant approach to QA, with recent graph-based variants addressing part of these issues by organizing knowledge to better support compositional questions. However, most textual graph-based RAG methods still lack the structure needed for symbolic operations useful to answer complex questions reliably. This motivates symbolic graph-based approaches, which extract knowledge graphs (KGs) whose relations are logic predicates that enable SQL-like querying. Yet these pipelines typically use LLMs for KG extraction, which can introduce consistency issues, where extracted facts may violate commonsense ontology constraints. We propose a neuro-symbolic framework for ontology-grounded KG construction combining open-domain extraction, embedding-based canonicalization of types and predicates, and targeted LLM-based correction of ontology violations. By deferring corrections to a post-extraction stage, our method avoids repeated LLM calls, substantially reducing token usage while improving KG consistency and preserving downstream QA quality. Finally, we show that the extracted KGs are well suited for symbolic querying by measuring the occurrence of SPARQL graph patterns.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29168
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction
Loconte, Lorenzo
Hospedales, Timothy
Cornelio, Cristina
Artificial Intelligence
Machine Learning
Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic operations like aggregation or exhaustive listing. Retrieval-augmented generation has become the dominant approach to QA, with recent graph-based variants addressing part of these issues by organizing knowledge to better support compositional questions. However, most textual graph-based RAG methods still lack the structure needed for symbolic operations useful to answer complex questions reliably. This motivates symbolic graph-based approaches, which extract knowledge graphs (KGs) whose relations are logic predicates that enable SQL-like querying. Yet these pipelines typically use LLMs for KG extraction, which can introduce consistency issues, where extracted facts may violate commonsense ontology constraints. We propose a neuro-symbolic framework for ontology-grounded KG construction combining open-domain extraction, embedding-based canonicalization of types and predicates, and targeted LLM-based correction of ontology violations. By deferring corrections to a post-extraction stage, our method avoids repeated LLM calls, substantially reducing token usage while improving KG consistency and preserving downstream QA quality. Finally, we show that the extracted KGs are well suited for symbolic querying by measuring the occurrence of SPARQL graph patterns.
title Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.29168