Metraipolis › archive › dc_f1df3a72aa35
Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection — arXiv:2608.29617
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29617
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:47:55.631Z
- SHA-256 of the archived text
cc2bd5ac59bd9cc5bd6b3977707a51d1bb1ebe4ea98ef49db4cfec3d280e8170- Stable URL of this page
https://metraipolis.com/documento/dc_f1df3a72aa35
How to cite
Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection — arXiv:2608.29617 — arXiv (en), https://arxiv.org/abs/2608.29617 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1df3a72aa35 (Metraipolis archive dc_f1df3a72aa35, sha256 cc2bd5ac59bd9cc5bd6b3977707a51d1bb1ebe4ea98ef49db4cfec3d280e8170)
BibTeX
@misc{dcf1df3a72aa35,
title = {Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection — arXiv:2608.29617},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29617},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1df3a72aa35; sha256 cc2bd5ac59bd9cc5bd6b3977707a51d1bb1ebe4ea98ef49db4cfec3d280e8170},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29617. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.29617 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:28:26.785Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).