4 papers
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
Feiran Zhang, Yixin Wu, Zhenghua Wang +4
Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal tasks, but remain susceptible to hallucinations, where generated text deviates from the underlying…
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models…
Explainable Synthetic Image Detection through Diffusion Timestep Ensembling
Yixin Wu, Feiran Zhang, Tianyuan Shi +7
Recent advances in diffusion models have enabled the creation of deceptively real images, posing significant security risks when misused. In this study, we empirically show that di…
Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement
Xiaohua Wang, Zisu Huang, Feiran Zhang +5
The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to…