4 papers
ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
Zhengyue Zhao, Yingzi Ma, Somesh Jha +3
Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, suc…
Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning
Qinghe Ma, Zhen Zhao, Yiming Wu +3
Tool-augmented reasoning has emerged as a promising direction for enhancing the reasoning capabilities of multimodal large language models (MLLMs). However, existing studies mainly…
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
Nanxi Li, Zhengyue Zhao, Chaowei Xiao
Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingl…
PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Nanxi Li, Zhengyue Zhao, G. Edward Suh +2
Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing t…