Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness
Haoting Qian, Qingjie Zhang, Zhicong Huang, Cheng Hong, Han Qiu
cs.AI, cs.CL
Submitted: 2026-08-05
Comments: 19 pages, 7 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning
- GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
- The Llama 3 Herd of Models
- Editing Models with Task Arithmetic
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
- TOFU: A Task of Fictitious Unlearning for LLMs
- What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs
- MUSE: Machine Unlearning Six-Way Evaluation for Language Models
- UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
- CAP: Controllable Alignment Prompting for Unlearning in LLMs
- The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
- Qwen3 Technical Report
- Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
- Understanding the Dilemma of Unlearning for Large Language Models
- Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
- Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems