paper
Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats
paperactiveprovisional
multi-agentic-system-leveraging-open-source-llms-to-mitigate-disinformation-threats-5a55623f·1 events·first seen 16h agoAliases: Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats
Co-occurring entities
More like this (12)
open-source LLMsMulti-Component LLM AgentContagion Networks: Evaluator Bias Propagation in Multi-Agent LLM SystemsThe Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMsProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM AgentsMeasuring Epistemic Resilience of LLMs Under Misleading Medical ContextWhat Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?Latent Adversarial Robustification (LAR)Leveraging Audio-LLMs to Filter Speech-to-Speech Training DataCan LLMs Reliably Self-Report Adversarial Prefills, and How?Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model FamiliesAdversarial Creation and Detection of AI-Generated Social Bot Content
Recent events (1)
Multi-agent system using open-source LLMs outperforms GPT-4 on disinformation detection
A new arXiv preprint proposes a multi-agent system for automated disinformation detection that emulates human annotator decision-making through consensus mechanisms, cognitive diversity, and hierarchical structure. The system uses open-source models (LLaMA, Kimi, Qwen, DeepSeek, LLaMA-Nemotron) and is evaluated on English, Polish, Slovak, and Bulgarian datasets across three fact-checking tasks. Results claim superior performance over individual LLMs including GPT-4 and GPT-3.5, with transparency benefits from using open weights models.