Selected Publications

ACL 2026 Findings
OFFSIDE pipeline

OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models

Hao Zheng, Zirui Pang, Ling Li, Zhijie Deng, Yuhan Pu, Zhaowei Zhu, Xiaobo Xia, Jiaheng Wei

2025 · Project

TL;DR: OFFSIDE benchmarks multimodal unlearning with real-world football transfer rumors, revealing that current methods struggle to forget visual misinformation and remain vulnerable to recovery and prompt attacks.

ICML 2025 Workshop
GUARD pipeline

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Zhijie Deng, Chris Yuhao Liu, Zirui Pang, Xinlei He, Lei Feng, Qi Xuan, Zhaowei Zhu, Jiaheng Wei

2025

TL;DR: We propose Generation-time Unlearning via Adaptive Restriction and Detection (GUARD), a framework that enables dynamic unlearning during LLM generation.