TEGRA: Text Encoding With Graph and Retrieval Augmentation for Misinformation Detection

2026-02-11

AI Summary

This work addresses the limitations of misinformation detection caused by insufficient integration of external knowledge. The authors propose TEGRA, a novel framework that constructs a hybrid text-graph representation by jointly encoding input text with a knowledge graph and incorporates a domain-specific knowledge retrieval-augmented mechanism to achieve deep fusion between language models and external knowledge bases. Experimental results on multiple benchmark datasets demonstrate that TEGRA significantly outperforms approaches relying solely on language models, thereby validating the effectiveness of the proposed graph-structured modeling and retrieval-augmented strategy in enhancing the accuracy of misinformation detection.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Engineering

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Misinformation detection is a critical task that can benefit significantly from the integration of external knowledge, much like manual fact-checking. In this work, we propose a novel method for representing textual documents that facilitates the incorporation of information from a knowledge base. Our approach, Text Encoding with Graph (TEG), processes documents by extracting structured information in the form of a graph and encoding both the text and the graph for classification purposes. Through extensive experiments, we demonstrate that this hybrid representation enhances misinformation detection performance compared to using language models alone. Furthermore, we introduce TEGRA, an extension of our framework that integrates domain-specific knowledge, further enhancing classification accuracy in most cases.

Problem

• misinformation detection
• external knowledge
• knowledge integration
• text representation
• fact-checking

Innovation

• graph-based text encoding
• retrieval augmentation
• misinformation detection
• knowledge integration
• hybrid representation