Efficient Detection of Toxic Prompts in Large Language Models

被引：0

作者：

Liu, Yi ^{[1
]}

Yu, Junzhe ^{[2
]}

Sun, Huijia ^{[2
]}

Shi, Ling ^{[1
]}

Deng, Gelei ^{[1
]}

Chen, Yuqi ^{[2
]}

Liu, Yang ^{[1
]}

机构：

[1] Nanyang Technological University, Singapore, Singapore

[2] ShanghaiTech University, Shanghai, China

来源：

arXiv | 1600年

关键词：

D O I：

暂无

中图分类号：

学科分类号：

摘要：

引用

共 50 条

[41] Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
Luo, Gen
Zhou, Yiyi
Ren, Tianhe
Chen, Shengxin
Sun, Xiaoshuai
Ji, Rongrong
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[42] Mitigating Hallucinations in Large Language Models via Semantic Enrichment of Prompts: Insights from BioBERT and Ontological Integration
Penkov, Stanislav
PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE COMPUTATIONAL LINGUISTICS IN BULGARIA, CLIB 2024, 2024, : 272 - 276
[43] Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation
University of Calabria, Italy
arXiv, 1600,
[44] GenKP: generative knowledge prompts for enhancing large language modelsGenKP: generative knowledge prompts for enhancing large language modelsX. Li et al.
Xinbai Li
Shaowen Peng
Shuntaro Yada
Shoko Wakamiya
Eiji Aramaki
Applied Intelligence, 2025, 55 (7)
[45] Do Large Language Models Generate Similar Codes from Mutated Prompts? A Case Study of Gemini Pro
Patel, Hetvi
Shah, Kevin Amit
Mondal, Shouvick
COMPANION PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON THE FOUNDATIONS OF SOFTWARE ENGINEERING, FSE COMPANION 2024, 2024, : 671 - 672
[46] Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts
Lan, Yunshi
Li, Xiang
Liu, Xin
Li, Yang
Qin, Wei
Qian, Weining
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 4389 - 4400
[47] Comparative Analysis of Prompt Strategies for Large Language Models: Single-Task vs. Multitask Prompts
Gozzi, Manuel
Di Maio, Federico
ELECTRONICS, 2024, 13 (23):
[48] A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
National Key Laboratory for Novel Software Technology, Nanjing University, China
不详
arXiv,
[49] From Images to Textual Prompts: Zero-shot Visual Question Answering with Frozen Large Language Models
Guo, Jiaxian
Li, Junnan
Li, Dongxu
Tiong, Anthony Meng Huat
Li, Boyang
Tao, Dacheng
Hoi, Steven
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 10867 - 10877
[50] Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation
Cantini, Riccardo
Cosenza, Giada
Orsino, Alessio
Talia, Domenico
DISCOVERY SCIENCE, DS 2024, PT I, 2025, 15243 : 52 - 68

← 1 2 3 4 5 →