GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis ACL

Yueqi Xie | Minghong Fang | Renjie Pi | Neil Gong |

SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark ACL

Zhenwen Liang | Kehan Guo | Gang Liu | Taicheng Guo | Yujun Zhou | Tianyu Yang | Jiajun Jiao | Renjie Pi | Jipeng Zhang | Xiangliang Zhang |

Plum: Prompt Learning using Metaheuristics F i n d i n g s - A C L

Rui Pan | Shuo Xing | Shizhe Diao | Wenhe Sun | Xiang Liu | KaShun Shum | Jipeng Zhang | Renjie Pi | Tong Zhang |

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts EMNLP

Ruida Wang | Jipeng Zhang | Yizhen Jia | Rui Pan | Shizhe Diao | Renjie Pi | Tong Zhang |

MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP

Renjie Pi | Tianyang Han | Jianshu Zhang | Yueqi Xie | Rui Pan | Qing Lian | Hanze Dong | Jipeng Zhang | Tong Zhang |

Mitigating the Alignment Tax of RLHF EMNLP

Yong Lin | Hangyu Lin | Wei Xiong | Shizhe Diao | Jianmeng Liu | Jipeng Zhang | Rui Pan | Haoxiang Wang | Wenbin Hu | Hanning Zhang | Hanze Dong | Renjie Pi | Han Zhao | Nan Jiang | Heng Ji | Yuan Yao | Tong Zhang |

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs EMNLP

Tianyang Han | Qing Lian | Rui Pan | Renjie Pi | Jipeng Zhang | Shizhe Diao | Yong Lin | Tong Zhang |