Cascade：面向大语言模型遗忘的分层可恢复性控制

Computer Science > Computation and Language arXiv:2609.16890 (cs) [Submitted on 15 Sep 2026] Title:Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning Authors:Qingchen Yu, Shiying Duan, Xiaodong Li, Yuhua Wang, Zhiyu Li, Shiji Zhou, Yifan Sun, Zhaoxin Fan View a PDF of the paper titled Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning, by Qingchen Yu and 7 other authors View PDF HTML (experimental) 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. Comments: Subjects: Computation and Language (cs.CL) Cite as: arXiv:2609.16890 [cs.CL] (or arXiv:2609.16890v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2609.16890 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Qingchen Yu [view email] [v1] Tue, 15 Sep 2026 09:23:16 UTC (981 KB) Full-text links: Access Paper: View a PDF of the paper titled Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning, by Qingchen Yu and 7 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-09 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)