Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety 文章

ArXiv CS.CL2026-08-05PAPERen作者: Caitlin A. Stamatis, Jonah Meyerhoff, Richard Zhang, Olivier Tieleman, Matteo Malgaroli, Thomas D. Hull
查看原文 →
关系图谱

Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety · 相关技术

相关技术

Counterfactual Evidence DisentanglementConvComputerized Adaptive TestingCausal Influence DiagramsCROPCOntExtCOMCCDBenchmarkAutomatic train operationAttention-based multiple instance learningArtificial Language LearningAdaptive Batch ScalingATEANNAI safetyAHATACEAbstractArmACT