collaborators

6 papers

cs.CL2025

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Song Wang, Zihan Chen, Peng Wang +5

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or special…

cs.CR2025

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender

Weixiang Zhao, Jiahe Guo, Yulin Hu +8

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but re…

cs.CL2025

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs

Weixiang Zhao, Yulin Hu, Yang Deng +8

Role-playing enables large language models (LLMs) to engage users in immersive and personalized interactions, but it also introduces significant safety risks. Existing role-play fi…

cs.CL2025

MPO: Multilingual Safety Alignment via Reward Gap Optimization

Weixiang Zhao, Yulin Hu, Yang Deng +8

Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across di…

cs.CV2025

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

Chenhang Cui, An Zhang, Yiyang Zhou +4

The recent advancements in large language models (LLMs) and pre-trained vision models have accelerated the development of vision-language large models (VLLMs), enhancing the intera…

cs.CL2024

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

Chenhang Cui, Gelei Deng, An Zhang +5

Recent advances in Large Vision-Language Models (LVLMs) have showcased strong reasoning abilities across multiple modalities, achieving significant breakthroughs in various real-wo…