Knowledge-Graph Multi-Agent Fact-Checking System
Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection
The system outperforms Llama 3.3 70B in fact-checking accuracy, offering a more reliable approach for content verification in information-heavy environments.
This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning. The system uses a memory-first, web-fallback architecture with Sentence-BERT-based semantic retrieval and Natural Language Inference. On a COVID-19 misinformation benchmark, it achieves 97.4% accuracy and 92.6% macro F1-score, outperforming a Llama 3.3 70B baseline.
Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection
This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning for explainable misinformation detection. The proposed system follows a memory-first, web-fallback architecture, in which input claims are initially evaluated against a dual-index Knowledge Graph through Sentence-BERT-based semantic retrieval and Natural Language Inference. When the evidence retrieved from the graph is insufficient to support a reliable decision, the framework collects information from trusted web sources and assesses it using an adversarial tribunal composed of support, contradiction, and judging agents. A graph-aware confidence mechanism combines semantic similarity, NLI confidence, and structural graph evidence to determine whether internal knowledge is sufficient, thereby reducing unnecessary web retrieval. Following verification, validated information is transformed into structured triples and incorporated into the Knowledge Graph, supporting the incremental expansion of the system's semantic memory. Experimental evaluation on a curated COVID-19 misinformation benchmark demonstrates that the proposed framework achieves an accuracy of 97.4\% and a macro-averaged F1-score of 92.6% on resolved claims, outperforming a Llama~3.3~70B baseline, which obtains an accuracy of 87.7% and a macro-averaged F1-score of 86.3%.
