4 papers
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Yuying Li, Leqi Zheng, Yongzi Yu +6
On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on…
Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
Zeyang Ding, Xinglin Hu, Jicong Fan
Hallucinations in large language models (LLMs) remain a central obstacle to trustworthy deployment, motivating detectors that are accurate, lightweight, and broadly applicable. Sin…
Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
Xiaoyun Zhang, Zhengyue Zhao, Wenxuan Shi +3
With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignm…
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization
Pucheng Dang, Xing Hu, Dong Li +3
Current text-to-image (T2I) synthesis diffusion models raise misuse concerns, particularly in creating prohibited or not-safe-for-work (NSFW) images. To address this, various safet…