Model Releases
Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection
arXiv:2608.29617v1 Announce Type: cross Abstract: This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning fo
arXiv:2608.29617v1 Announce Type: cross Abstract: 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 Llama3.370B baseline, which obtains an accuracy of 87.7% and a macro-averaged F1-score of 86.3%.
Related
- Beyond Verdicts: A Graph-Based Analysis of Human and LLM Reasoning in Scientific Fact-Checking
- Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification
- MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment
- TRUST Agents: A Collaborative Multi-Agent Framework for Fake News Detection, Explainable Verification, and Logic-Aware Claim Reasoning
- VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checking
Source: arXiv cs.AI | 2026-09-01