collaborators

12 papers

cs.CL2026

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

Xinjie Shen, Rongzhe Wei, Peizhi Niu +6

Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, increas…

cs.AI2026

Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching

Rongzhe Wei, Ge Shi, Min Cheng +5

Large Language Models (LLMs) have significantly advanced tool-augmented agents, enabling autonomous reasoning via API interactions. However, executing multi-step tasks within massi…

cs.LG2026

GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints

Andy Zhu, Rongzhe Wei, Yupu Gu +1

Machine unlearning (MU) for large language models has become critical for AI safety, yet existing methods fail to generalize to Mixture-of-Experts (MoE) architectures. We identify…

cs.LG2026

MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs

Yupu Gu, Rongzhe Wei, Andy Zhu +1

Knowledge editing (KE) enables precise modifications to factual content in large language models (LLMs). Existing KE methods are largely designed for dense architectures, limiting…

cs.LG2026

Differentially Private Relational Learning with Entity-level Privacy Guarantees

Yinan Huang, Haoteng Yin, Eli Chien +2

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Priva…

cs.CR2025

The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search

Rongzhe Wei, Peizhi Niu, Xinjie Shen +7

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the p…