Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning

arXiv:2609.16890 · cs.CL · Submitted 2026-09-15 · Read on arXiv

cs.CL

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: Accepted by EMNLP 2026 (Findings)

Code: https://github.com/Noryxen/Cascade

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Forget ROUGE — 18× in this paper
• Benchmark — 15× in this paper · explained in 2 episodes
• Large Language Model — 15× in this paper
• Accuracy — 14× in this paper · explained in 1 episode
• Extraction Strength — 11× in this paper
• Decode — 10× in this paper · explained in 2 episodes
• Robustness — 10× in this paper · explained in 5 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Machine Unlearning — 7× in this paper · explained in 2 episodes
• AUC — 5× in this paper · explained in 2 episodes
• Truth Ratio — 4× in this paper
• Benchmarking — 2× in this paper · explained in 3 episodes
• Forget Probability — 2× in this paper
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Approximate Unlearning — 1× in this paper · explained in 1 episode
• Balanced Unlearning Score — 1× in this paper
• Composite Forgetting Index — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Hallucination Detection — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• Who's Harry Potter? Approximate Unlearning in LLMs
• Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
• The Llama 3 Herd of Models
• GPT-4 Technical Report
• Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
• Mask-Free Privacy Extraction and Rewriting: A Domain-Aware Approach via Prototype Learning
• Lyapunov Probes for Hallucination Detection in Large Foundation Models
• Hyperbolic Large Language Models
• Dissecting Language Models: Machine Unlearning via Selective Pruning
• A Survey on Unlearning in Large Language Models
• Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering