activity
20242026
collaborators

5 papers

cs.CL2026

A Few Neurons Reveal When LLMs Misuse Tools: Sparse Detection and Selective Steering for Reliable Tool Use

Yutong Ke, Ming Yin, Chongwen Zhao +1

Agentic LLMs exhibit three consequential tool-use failures: invalid arguments (validity), unnecessary calls (over-calling), and omitted calls when tools are needed (missing). We fi…

cs.AI2025

SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models

Qinjian Zhao, Jiaqi Wang, Zhiqiang Gao +3

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as j…

cs.AI2025

Unraveling LLM Jailbreaks Through Safety Knowledge Neurons

Chongwen Zhao, Yutong Ke, Kaizhu Huang

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models fo…

cs.CV2025

Discrete Wavelet Transform-Based Capsule Network for Hyperspectral Image Classification

Zhiqiang Gao, Jiaqi Wang, Hangchi Shen +3

Hyperspectral image (HSI) classification is a crucial technique for remote sensing to build large-scale earth monitoring systems. HSI contains much more information than traditiona…

cs.AI2024

Defending against Jailbreak through Early Exit Generation of Large Language Models

Chongwen Zhao, Zhihao Dou, Kaizhu Huang

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models fo…