HyDRA: A Hybrid-Driven Reasoning Architecture for Verifiable Knowledge Graphs

2025-07-21

AI Summary

Automated knowledge graph (KG) construction faces core challenges including unreliable outputs, structural inconsistencies (e.g., isolated nodes, class–instance confusion), and unverifiable results. To address these, we propose a neuro-symbolic, contract-driven approach grounded in the Design-by-Contract (DbC) paradigm. Our method introduces a verifiable hybrid reasoning architecture that integrates large language models (LLMs) with the SymbolicAI framework to enable ontology-guided triple extraction. We further design a verifiable contract mechanism and a functional correctness evaluation framework to jointly ensure process controllability and result verifiability. Experiments demonstrate significant improvements in KG structural consistency and semantic accuracy, while enabling end-to-end traceable verification. All code is publicly released.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Description Logics
• Machine Learning: Neuro-Symbolic Learning

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The synergy between symbolic knowledge, often represented by Knowledge Graphs (KGs), and the generative capabilities of neural networks is central to advancing neurosymbolic AI. A primary bottleneck in realizing this potential is the difficulty of automating KG construction, which faces challenges related to output reliability, consistency, and verifiability. These issues can manifest as structural inconsistencies within the generated graphs, such as the formation of disconnected $ extit{isolated islands}$ of data or the inaccurate conflation of abstract classes with specific instances. To address these challenges, we propose HyDRA, a $ extbf{Hy}$brid-$ extbf{D}$riven $ extbf{R}$easoning $ extbf{A}$rchitecture designed for verifiable KG automation. Given a domain or an initial set of documents, HyDRA first constructs an ontology via a panel of collaborative neurosymbolic agents. These agents collaboratively agree on a set of competency questions (CQs) that define the scope and requirements the ontology must be able to answer. Given these CQs, we build an ontology graph that subsequently guides the automated extraction of triplets for KG generation from arbitrary documents. Inspired by design-by-contracts (DbC) principles, our method leverages verifiable contracts as the primary control mechanism to steer the generative process of Large Language Models (LLMs). To verify the output of our approach, we extend beyond standard benchmarks and propose an evaluation framework that assesses the functional correctness of the resulting KG by leveraging symbolic verifications as described by the neurosymbolic AI framework, $ extit{SymbolicAI}$. This work contributes a hybrid-driven architecture for improving the reliability of automated KG construction and the exploration of evaluation methods for measuring the functional integrity of its output. The code is publicly available.

Problem

• Automating reliable Knowledge Graph construction with verifiability
• Addressing structural inconsistencies in generated Knowledge Graphs
• Ensuring functional correctness in neurosymbolic AI-driven KG generation

Innovation

• Hybrid-driven reasoning architecture for KG automation
• Ontology construction via collaborative neurosymbolic agents
• Verifiable contracts control LLM generative process