Research
Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning
arXiv:2609.16890v1 Announce Type: new Abstract: Large Language Model (LLM) unlearning is essential for removing sensitive or copyrighted knowledge while preserving general utility. Existing methods of
arXiv:2609.16890v1 Announce Type: new Abstract: Large Language Model (LLM) unlearning is essential for removing sensitive or copyrighted knowledge while preserving general utility. Existing methods often leave residual knowledge in intermediate representations, which can still be recovered. To address this, we propose Cascade, a hierarchical recoverability control framework that minimizes the internal identifiability of target knowledge. Cascade combines three complementary controls: path-level routing to suppress privacy-associated activation routes, representation-level compression to reduce geometric separability, and decoding-level intervention to limit residual recovery. Experiments on TOFU, MUSE-News, and WMDP, including robustness tests with query reformulation and extraction-style prompts, show that Cascade effectively reduces recoverability while maintaining stable model utility.
Related
- Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
- Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
- On the Recoverability of Private Information Unlearning in Large Language Models
Source: arXiv cs.CL | 2026-09-16