A Brief Survey on Safety of Large Language Models
Journal of Computing and Information Technology · 15.07.2024 · 32 (1) · 47-64
DOI: 10.20532/cit.2024.1005778 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing and Information Technology, online erschienen am 15.07.2024. Verfasst von Zhengjie Gao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) and have been widely adopted in various applications such as machine translation, chatbots, text summarization, and so on. However, the use of LLMs has raised concerns about their potential safety and security risks. In this survey, we explore the safety implications of LLMs, including ethical considerations, hallucination, and prompt injection. We also discuss current research efforts to mitigate these risks and identify areas for future research. Our survey provides a comprehensive overview of the safety concerns related to LLMs, which can help researchers and practitioners in the NLP community develop more safe and ethical applications of LLMs.
Zitieren
APA
Gao, Z., Liu, X., Lan, Y., & Yang, Z. (2024). A Brief Survey on Safety of Large Language Models. Journal of Computing and Information Technology, 32(1), 47-64. https://doi.org/10.20532/cit.2024.1005778
Vancouver
Gao Z, Liu X, Lan Y, Yang Z. A Brief Survey on Safety of Large Language Models. Journal of Computing and Information Technology. 2024;32(1):47-64. doi:10.20532/cit.2024.1005778
BibTeX
@article{Gao2024,
author = {Gao, Zhengjie and Liu, Xuanzi and Lan, Yuanshuai and Yang, Zheng},
title = {A Brief Survey on Safety of Large Language Models},
journal = {Journal of Computing and Information Technology},
year = {2024},
volume = {32},
number = {1},
pages = {47--64},
doi = {10.20532/cit.2024.1005778}
}
EUVIMED