Back to papers
October 8, 2026cs.CLcs.AIcs.LG

Predicting Alignment Generalization with Value Representations

Andy Liu, Mehar Bhatia, Karolina Stanczak, Mona Diab, Vered Shwartz, Daniel Fried
Read on arXivDownload PDF
Categories

cs.CL, cs.AI, cs.LG

Predicting Alignment Generalization with Value Representations - AI Research | One9Founders