arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Huazhong University of Science and Technology(华中科技大学)

2025-12-30 至 2025-12-30 共收录 3
2306.05499 2025-12-30 cs.CR cs.AI cs.CL cs.SE

Prompt Injection attack against LLM-integrated Applications

针对集成大语言模型应用的提示注入攻击

Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Zihao Wang, Xiaofeng Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, Leo Yu Zhang, Yang Liu

机构 * Griffith University(格里菲斯大学) Nanyang Technological University(南洋理工大学) University of New South Wales(新南威尔士大学) Huazhong University of Science and Technology(华中科技大学) Indiana University at Bloomington(印第安纳大学布卢明顿分校) Southern University of Science and Technology(南方科技大学) Tianjin University(天津大学)

AI总结 本研究提出HouYi技术,揭示LLM集成应用中提示注入攻击的潜在风险及缓解方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22629 2025-12-30 cs.AI cs.IR

DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation

DICE:基于概率评分的离散可解释比较评估用于检索增强生成

Shiyan Liu, Jian Ma, Rui Qu

机构 * School of Computer Science and Technology(计算机科学与技术学院) Huazhong University of Science and Technology(华中科技大学)

AI总结 DICE提出一种基于概率评分的两阶段框架,提升RAG评估的可解释性和稳健性,通过透明判断和系统性错误诊断,实现高效且可信的评估。

Comments Accepted at ResponsibleFM @ NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03332 2025-12-30 cs.LG cs.AI

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models

探索分层信息有效性以实现小语言模型的后训练量化

He Xiao, Qingyao Yang, Dirui Xie, Wendong Xu, Zunhai Su, Runming yang, Wenyong Zhou, Haobo Liu, Zhengwu Liu, Ngai Wong

机构 * The University of Hong Kong(香港大学) Huazhong University of Science and Technology(华中科技大学) Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生学院)

AI总结 LieQ通过分层信息有效性量化方法,在亚8B模型中实现高效低比特压缩,减少精度损失并提升边缘设备部署可行性。

Comments low-bit quantization

详情

展开后加载摘要…

URL PDF HTML 收藏