Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection

• URL: http://arxiv.org/abs/2608.29617v1
• Date: Sun, 30 Aug 2026 07:16:07 GMT
• Title: Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection
• Abstract summary: This paper introduces a hybrid fact-checking framework that integrates Knowledge Graph-based semantic memory with adversarial multi-agent reasoning for explainable misinformation detection.<n>The proposed system follows a memory-first, web-fallback architecture, in which input claims are initially evaluated against a dual-index Knowledge Graph.<n>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.
• Score: 42.698418800007865
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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 Llama~3.3~70B baseline, which obtains an accuracy of 87.7% and a macro-averaged F1-score of 86.3%.

Related papers

• From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism [23.0538048682894]
  We model the terminal retrieval stage with a causal graph grounded in Reichenbach's common cause principle.<n>Since a retrieved document is a collider (A -> d - B), retrieval itself opens an associational path between the query and B.<n>Unlike causality-enhanced RAG variants that model causal relations inside the knowledge content, our graph models the causal structure of the retrieval process itself.
  arXiv  Detail & Related papers  (2026-08-22T00:31:06Z)
• What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition [36.08108046941572]
  Graph neural networks are widely used for node classification, but they remain vulnerable to out-of-distribution (OOD) shifts in node features and graph structure.<n>We propose TIDE, a novel and effective Tri-Component Information Decomposition framework that explicitly decomposes information into feature-specific, structure-specific and joint components.<n>Extensive experiments across seven datasets confirm the efficacy of TIDE, achieving up to a 34% improvement in FPR95 over strong baselines.
  arXiv  Detail & Related papers  (2026-05-13T05:36:33Z)
• Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge [0.0]
  Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts.<n>We propose Smart, a framework that augments dense embeddings with three explicit properties -- temporal awareness, confidence decay, and relational awareness.
  arXiv  Detail & Related papers  (2026-04-22T14:13:50Z)
• IE as Cache: Information Extraction Enhanced Agentic Reasoning [82.00741114456727]
  Information Extraction aims to distill structured, decision-relevant information from unstructured text.<n>We propose textitIE-as-Cache, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning.
  arXiv  Detail & Related papers  (2026-04-16T12:18:27Z)
• Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity [66.94391219005291]
  This paper proposes Agentic Cognitive Profiling (ACP), an agentic framework that realigns automated screening with clinical protocol logic.<n>Central to our design is decoupling semantic understanding from measurement by delegating all quantification to deterministic function calling.<n>ACP achieves 90.5% score match rate in task examination and 85.3% accuracy in AD prediction, surpassing popular baselines.
  arXiv  Detail & Related papers  (2026-03-18T06:15:35Z)
• CLUE: Non-parametric Verification from Experience via Hidden-State Clustering [64.50919789875233]
  We show that correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations.<n>ClUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates.
  arXiv  Detail & Related papers  (2025-10-02T02:14:33Z)
• Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Audits [0.0]
  Hound is a relation-first graph engine that improves system-level reasoning across interrelated components in complexs.<n>A second contribution is a persistent belief system: long-lived vulnerability hypotheses whose confidence is updated as evidence accrues.
  arXiv  Detail & Related papers  (2025-09-29T02:46:02Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection [84.75972919995398]
  This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles.<n>The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent, and (iv) a web-scraped data analyzer.<n>Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches.
  arXiv  Detail & Related papers  (2025-08-13T19:14:48Z)
• ClaimTrust: Propagation Trust Scoring for RAG Systems [7.7690689135107425]
  ClaimTrust is a propagation-based trust scoring framework that dynamically evaluates the reliability of documents in a RAG system.<n>We preprocess and analyze 814 political news articles to extract 2,173 unique claims and classify 965 meaningful relationships.<n>ClaimTrust iteratively updates trust scores until convergence, effectively differentiating trustworthy articles from unreliable ones.
  arXiv  Detail & Related papers  (2025-03-12T07:52:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.