7 citations · 9 across the 13 of their papers we have counts for
7 papers · 1 filter
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
Xinjie Shen, Junran Wang, Rongzhe Wei +1
Language-model agents increasingly use tools to act on external systems. Earlier actions can alter files, permissions, database records, or other state, making a later routine-look…
Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths
Jialu Wang, Peizhi Niu, Haoteng Yin +3
While an unlearned language model may no longer recall a fact directly, the fact often remains recoverable through multi-hop reasoning over related knowledge. Most existing unlearn…
What Must a World Model Distinguish for Planning?
Rongzhe Wei, Hans Hao-Hsun Hsu, Peizhi Niu +2
World models simulate the consequences of action candidates, but good planning need not preserve every physical distinction required for accurate prediction. We formalize this gap…
One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
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, attacke…
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…
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…
GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints
Andy Zhu, Rongzhe Wei, Yupu Gu +1
Machine unlearning in Mixture-of-Experts (MoE) large language models presents a critical yet under-explored challenge. Current unlearning methods applied to MoE architectures often…