5 papers
Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models
Yangmin Huang, Shu Quan, He Geng +5
Medical knowledge changes continually, making large language models vulnerable to relying on outdated yet clinically plausible information. We study whether the format of supervisi…
A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models
Shu Quan, Tianfang Hao, Sitong Fang +8
Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equal…
ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection
He Geng, Yangmin Huang, Lixian Lai +5
Aligning Large Language Models (LLMs) with high-stakes medical standards remains a significant challenge, primarily due to the dissonance between coarse-grained preference signals…
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models
Shuliang Liu, Hongyi Liu, Aiwei Liu +7
The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditi…
VLA-Mark: A cross modal watermark for large vision-language alignment model
Shuliang Liu, Qi Zheng, Jesse Jiaxi Xu +8
Vision-language models demand watermarking solutions that protect intellectual property without compromising multimodal coherence. Existing text watermarking methods disrupt visual…