7 papers
Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking
Huizhong Guo, Tianjun Wei, Dongxia Wang +4
Large language models (LLMs) are increasingly applied to ranking tasks in retrieval and recommendation. Although reasoning prompting can enhance ranking utility, our preliminary ex…
MAS: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
Kun Wang, Guibin Zhang, ManKit Ye +6
The past two years have witnessed the meteoric rise of Large Language Model (LLM)-powered multi-agent systems (MAS), which harness collective intelligence and exhibit a remarkable…
RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments
Yuchuan Fu, Xiaohan Yuan, Dongxia Wang
The rapid deployment of Large language model (LLM) agents in critical domains like healthcare and finance necessitates robust security frameworks. To address the absence of standar…
Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity
Qi Zhou, Jie Zhang, Dongxia Wang +5
Human preference plays a crucial role in the refinement of large language models (LLMs). However, collecting human preference feedback is costly and most existing datasets neglect…
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Kun Wang, Guibin Zhang, Zhenhong Zhou +100
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communi…
TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer
Zhihong Xu, Dongxia Wang, Peng Du +2
Pose-Guided Person Image Synthesis (PGPIS) generates images that maintain a subject's identity from a source image while adopting a specified target pose (e.g., skeleton). While di…
Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
Qi Zhou, Tianlin Li, Qing Guo +4
Recent studies have raised significant concerns regarding the vulnerability of Large Vision Language Models (LVLMs) to maliciously injected or perturbed input images, which can mis…