ResearchBenchmarksAutomated Fact Checking on FactorsFollow70.8Macro F1CAAFC53.32857.86462.466.936May 12, 2026Evaluation ResultsMethodMethodLinksMacro F1AccuracyCAAFCBackbone Model=LLAMA3....Backbone Model=LLAMA3.3-70B2026.0570.893.1CAAFCBackbone Model=GEMMA3-27BBackbone Model=GEMMA3-27B2026.0569.391.9CAAFCBackbone Model=GPT-OSS...Backbone Model=GPT-OSS-120B2026.055477.4