4 citations · 5 across the 7 of their papers we have counts for
8 papers
Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution
Guoxin Shi, Haoyu Wang, Zaihui Yang +2
Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on static adversarial settings, whic…
UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
Haotian Luo, Huaisong Zhang, Xuelin Zhang +15
Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical…
Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
Yilun Kong, Guozheng Ma, Qi Zhao +4
Despite recent advancements in offline multi-task reinforcement learning (MTRL) have harnessed the powerful capabilities of the Transformer architecture, most approaches focus on a…
Lifelong Safety Alignment for Language Models
Haoyu Wang, Zeyu Qin, Yifei Zhao +4
LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing…
Safety Reasoning with Guidelines
Haoyu Wang, Zeyu Qin, Li Shen +3
Training safe LLMs remains a critical challenge. The most widely used method, Refusal Training (RT), struggles to generalize against various Out-of-Distribution (OOD) jailbreaking…
Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation
Haoyu Wang, Bingzhe Wu, Yatao Bian +3
Large Language Models (LLMs) are implicit troublemakers. While they provide valuable insights and assist in problem-solving, they can also potentially serve as a resource for malic…
Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
Haoyu Wang, Guozheng Ma, Ziqiao Meng +9
Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and…
Are Large Language Models Really Robust to Word-Level Perturbations?
Haoyu Wang, Guozheng Ma, Cong Yu +10
The swift advancement in the scales and capabilities of Large Language Models (LLMs) positions them as promising tools for a variety of downstream tasks. In addition to the pursuit…