2 papers
cs.CL2026
Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning
Qingchen Yu, Shiying Duan, Xiaodong Li +5
Large Language Model (LLM) unlearning is essential for removing sensitive or copyrighted knowledge while preserving general utility. Existing methods often leave residual knowledge…
cs.CL2026
A Hyperbolicity Atlas of Large Language Model Hidden States
Zhichao Yang, Yuanze Hu, Gen Li +7
LLM hidden states are ordinary vectors, but the distances among those vectors may still show hierarchical structure. To our knowledge, this paper is the first systematic study of w…