6 papers
GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization
Yu Pan, Andi Zhang, Yi Wang +2
Diffusion Vision-Language Models (dVLMs), built upon the non-causal foundations of Diffusion Large Language Models (dLLMs), have demonstrated remarkable efficacy in multimodal task…
Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models
Yue Xu, Chengyan Fu, Li Xiong +2
Pre-training large language models (LLMs) on vast text corpora enhances natural language processing capabilities but risks encoding social biases, particularly gender bias. While p…
From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship
Yue Xu, Wenjie Wang
Multimodal large language models (MLLMs) have shown impressive capabilities across tasks involving both visual and textual modalities. However, growing concerns remain about their…
DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning
Hongye Qiu, Yue Xu, Yi Wang +2
Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising fairness con…
: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models
Fenghua Weng, Yue Xu, Chengyan Fu +1
As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real…
Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models
Yue Xu, Xiuyuan Qi, Zhan Qin +1
Multimodal Large Language Models (MLLMs) extend the capacity of LLMs to understand multimodal information comprehensively, achieving remarkable performance in many vision-centric t…