Back to papers
September 28, 2026cs.CL

Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context

Muyu He, Yuchen Liu, Ran Tao, Li Zhang
Read on arXivDownload PDF
Categories

cs.CL

Late Attention Layers Alone Can Copy Entity Tokens, but Not Without Attending to Their Context | One9Founders