21 citations · 27 across the 8 of their papers we have counts for
9 papers
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
Sitong Fang, Shiyi Hou, Kaile Wang +6
Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidiou…
RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
Bang An, Shiyue Zhang, Mark Dredze
Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented…
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
Borong Zhang, Yuhao Zhang, Jiaming Ji +5
Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the r…
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Jiaming Ji, Jiayi Zhou, Hantao Lou +16
Reinforcement learning from human feedback (RLHF) has proven effective in enhancing the instruction-following capabilities of large language models; however, it remains underexplor…
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
Josef Dai, Tianle Chen, Xuyao Wang +4
To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human value…
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
Jiaming Ji, Donghai Hong, Borong Zhang +10
In this study, we introduce the safety human preference dataset, PKU-SafeRLHF, designed to promote research on safety alignment in large language models (LLMs). As a sibling projec…
Language Models Resist Alignment: Evidence From Data Compression
Jiaming Ji, Kaile Wang, Tianyi Qiu +7
Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, so…
Reward Generalization in RLHF: A Topological Perspective
Tianyi Qiu, Fanzhi Zeng, Jiaming Ji +7
Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune langua…
Safe RLHF: Safe Reinforcement Learning from Human Feedback
Josef Dai, Xuehai Pan, Ruiyang Sun +5
With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tensio…