Reducing Political Manipulation with Consistency Training 文章

ArXiv CS.CL2026-05-29NEWSen作者: Long Phan, Devin Kim, Alexander Pan, Alice Blair, Adam Khoja, Dan Hendrycks
查看原文 →
关系图谱

Reducing Political Manipulation with Consistency Training · 相关技术

相关技术

Large language modelSentiment ConsistencyRLHelpfulness Consistency TrainingSentiment Consistency TrainingPolitical Consistency Training