Qizhou Wang

LLM Unlearning with LLM Beliefs

Towards Understanding Valuable Preference Data for Large Language Model Alignment

Memorize to Forget: Machine Unlearning without Gradient Ascent via Model Extrapolation

AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models

EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget

On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model

Explainable LLM Unlearning through Reasoning

What Is Preference Optimization Doing, How and Why?

Lifelong Unlearning for Multimodal Large Language Models

Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning

Adaptive Localization of Knowledge Negation for Continual LLM Unlearning

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning

Strengthening Federated Learning: Surrogate Data-Guided Aggregation for Robust Backdoor Defense

Rectifying Gradient-based OOD Detection via Fisher Information Matrix