HybridFC: A Hybrid Fact-Checking Approach for Knowledge Graphs
Umair Qudus, Michael Roeder, Muhammad Saleem, Axel-Cyrille Ngonga Ngomo
TL;DR
HybridFC addresses the veracity prediction of knowledge-graph assertions by ensembling text-, path-, and KG-embedding-based fact-checking signals. It introduces three dedicated components that extract and encode evidence from text, KG paths, and embeddings, then fuses their outputs with a neural network to produce a final veracity score. On FactBench and BirthPlace/DeathPlace benchmarks, HybridFC with TransE embeddings achieves state-of-the-art AUROC improvements (approximately 0.14–0.27 on FactBench) and strong results on BD, demonstrating the value of combining diverse modalities. The work provides open-source code and reproducible evaluation, underscoring the practical impact of modular, hybrid architectures for scalable KG veracity assessment.
Abstract
We consider fact-checking approaches that aim to predict the veracity of assertions in knowledge graphs. Five main categories of fact-checking approaches for knowledge graphs have been proposed in the recent literature, of which each is subject to partially overlapping limitations. In particular, current text-based approaches are limited by manual feature engineering. Path-based and rule-based approaches are limited by their exclusive use of knowledge graphs as background knowledge, and embedding-based approaches suffer from low accuracy scores on current fact-checking tasks. We propose a hybrid approach -- dubbed HybridFC -- that exploits the diversity of existing categories of fact-checking approaches within an ensemble learning setting to achieve a significantly better prediction performance. In particular, our approach outperforms the state of the art by 0.14 to 0.27 in terms of Area Under the Receiver Operating Characteristic curve on the FactBench dataset. Our code is open-source and can be found at https://github.com/dice-group/HybridFC.