Schema-Aware Planning and Hybrid Knowledge Toolset for Reliable Knowledge Graph Triple Verification

2026-04-05

AI Summary

This work addresses the limitations of existing knowledge graph triple validation methods, which often rely on single-source information and static reasoning, leading to poor performance on complex or long-tail facts and limited interpretability. To overcome these challenges, the authors propose SHARP, a novel framework that introduces, for the first time, a training-free autonomous agent architecture. SHARP reframes triple validation as a dynamic process of strategic planning, active investigation, and evidence-based reasoning. It integrates a memory-augmented mechanism, pattern-aware planning, and a hybrid knowledge toolkit to jointly leverage graph structural cues and external textual sources for cross-verification. Evaluated on FB15K-237 and Wikidata5M-Ind, SHARP achieves accuracy improvements of 4.2% and 12.9%, respectively, while generating transparent, traceable evidence chains that substantially enhance both robustness and interpretability.

Abstract

Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combines a Memory-Augmented Mechanism with Schema-Aware Strategic Planning to improve reasoning stability, and employs an enhanced ReAct loop with a Hybrid Knowledge Toolset to dynamically integrate internal KG structure and external textual evidence for cross-verification. Experiments on FB15K-237 and Wikidata5M-Ind show that SHARP significantly outperforms existing state-of-the-art baselines, achieving accuracy gains of 4.2% and 12.9%, respectively. Moreover, SHARP provides transparent, fact-based evidence chains for each judgment, demonstrating strong interpretability and robustness for complex verification tasks.

Problem

• Knowledge Graph
• Triple Verification
• Noise
• Single-source Bias
• Interpretability

Innovation

• Schema-Aware Planning
• Hybrid Knowledge Toolset
• Triple Verification
• ReAct Framework
• Memory-Augmented Reasoning