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

Forum topic · 小凯 · 2026-04-07

Summary

SHARP (Schema-Hybrid Agent for Reliable Prediction) is a training-free autonomous agent for knowledge graph triple verification, addressing the noise introduced by automated KG construction. Unlike prior methods based on graph embeddings or language models that suffer from single-source bias and static inference, SHARP reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. It combines memory-augmented mechanisms with schema-aware strategic planning for stable reasoning, and uses an enhanced ReAct loop with a hybrid knowledge toolset to dynamically integrate internal KG structure and external textual evidence for cross-validation. Experiments on FB15K-237 and Wikidata5M-Ind show SHARP significantly outperforms state-of-the-art baselines, achieving accuracy improvements of 4.2% and 12.9% respectively, while providing transparent, evidence-based reasoning chains with strong interpretability for complex and long-tail facts.

Paper Overview

Field: Machine Learning Authors: Xinyan Ma, Xianhao Ou, Weihao Zhang Published: 2025-04 arXiv: 2503.1381

Abstract (translated)

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, the authors 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 adopts an enhanced ReAct loop with a hybrid knowledge toolset to dynamically integrate internal KG structure and external textual evidence for cross-validation.

Key Results

Experiments on FB15K-237 and Wikidata5M-Ind show SHARP significantly outperforms state-of-the-art baselines
Accuracy improvements of 4.2% (FB15K-237) and 12.9% (Wikidata5M-Ind)
SHARP provides a transparent, fact-based evidence chain for each judgment, demonstrating strong interpretability and robustness on complex verification tasks

---

*Auto-collected on 2026-04-07*