Language Language Models (LLMs) face safety concerns due to potential misuse by malicious users. Recent red-teaming efforts have identified adversarial suffixes capable of jailbreaking LLMs using the gradient-based search algorithm Greedy Coordinate Gradient (GCG). However, GCG struggles with computational inefficiency, limiting further investigations regarding suffix transferability and scalability across models and data. In this work, we bridge the connection between search efficiency and suffix transferability. We propose a two-stage transfer learning framework, DeGCG, which decouples the search process into behavior-agnostic pre-searching and behavior-relevant post-searching. Specifically, we employ direct first target token optimization in pre-searching to facilitate the search process. We apply our approach to cross-model, cross-data, and self-transfer scenarios. Furthermore, we introduce an interleaved variant of our approach, i-DeGCG, which iteratively leverages self-transferability to accelerate the search process. Experiments on HarmBench demonstrate the efficiency of our approach across various models and domains. Notably, our i-DeGCG outperforms the baseline on Llama2-chat-7b with ASRs of $43.9$ ($+22.2$) and $39.0$ ($+19.5$) on valid and test sets, respectively. Further analysis on cross-model transfer indicates the pivotal role of first target token optimization in leveraging suffix transferability for efficient searching.
Enabling Doctor-Centric Medical AI with LLMs through Workflow-Aligned Tasks and Benchmarks
Shenzhen Research Institute of Big Data(大数据研究 institute);National Health Data Institute(国家健康数据研究所);Halmstad University(哈马碧大学);Shenzhen University of Advanced Technology(深圳先进技术大学)
Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation
University of British Columbia(不列颠哥伦比亚大学);Texas Tech University(德克萨斯技术大学);Institute for the Future of Education, Tecnológico de Monterrey(教育未来研究所,墨西哥蒙特雷技术学院)
CAPE: A Chinese Dataset for Appraisal-based Emotional Generation using Large Language Models
International Digital Economy Academy (IDEA)(国际数字经济学院(IDEA));University of Michigan(密歇根大学);Hong Kong University of Science and Technology(香港科技大学);University of California, Los Angeles(加州大学洛杉矶分校)
The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP
University of California, Los Angeles(加州大学洛杉矶分校);Georgia Institute of Technology(佐治亚理工学院);University of Wisconsin - Madison(威斯康星大学麦迪逊分校);University of Cape Coast(科克伍德大学);Carleton University(卡尔顿大学);Stetson University(史蒂文森大学);Northwestern University in Qatar(卡塔尔西北大学);Cornell University(康奈尔大学);Soka University of America(美国立命大学);Columbia University(哥伦比亚大学)