A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity

被引：69

作者：

Alawida, Moatsum ^{[1
]}

Mejri, Sami ^{[2
]}

Mehmood, Abid ^{[1
]}

Chikhaoui, Belkacem ^{[3
]}

Abiodun, Oludare Isaac ^{[4
]}

机构：

[1] Abu Dhabi Univ, Dept Comp Sci, POB 59911, Abu Dhabi, U Arab Emirates

[2] Khalifa Univ Sci & Technol, Ctr Teaching & Learning, POB 127788, Abu Dhabi, U Arab Emirates

[3] TELUQ Univ, Appl Artificial Intelligence Inst, Montreal, PQ H2S 3L5, Canada

[4] Univ Abuja, Dept Comp Sci, Gwagwalada 900110, Nigeria

来源：

INFORMATION | 2023年 / 14卷 / 08期

关键词：

ChatGPT; language generation; natural language processing (NLP); cybersecurity; ChatGPT applications; ARTIFICIAL-INTELLIGENCE; MEDICAL DEVICES;

D O I：

10.3390/info14080462

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents an in-depth study of ChatGPT, a state-of-the-art language model that is revolutionizing generative text. We provide a comprehensive analysis of its architecture, training data, and evaluation metrics and explore its advancements and enhancements over time. Additionally, we examine the capabilities and limitations of ChatGPT in natural language processing (NLP) tasks, including language translation, text summarization, and dialogue generation. Furthermore, we compare ChatGPT to other language generation models and discuss its applicability in various tasks. Our study also addresses the ethical and privacy considerations associated with ChatGPT and provides insights into mitigation strategies. Moreover, we investigate the role of ChatGPT in cyberattacks, highlighting potential security risks. Lastly, we showcase the diverse applications of ChatGPT in different industries and evaluate its performance across languages and domains. This paper offers a comprehensive exploration of ChatGPT's impact on the NLP field.

引用

页数：23

共 77 条

[31]

Li Q, 2021, Arxiv, DOI arXiv:2008.00364

[32] Chinese clinical named entity recognition with variant neural structures based on BERT methods [J].

Li, Xiangyang ;

Zhang, Huan ;

Zhou, Xiao-Hua .

JOURNAL OF BIOMEDICAL INFORMATICS, 2020, 107

[33]

Lin W., 2021, arXiv

[34] VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs [J].

Lin, Xudong ;

Bertasius, Gedas ;

Wang, Jue ;

Chang, Shih-Fu ;

Parikh, Devi ;

Torresani, Lorenzo .

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :7001-7011

[35]

Litman D, 2016, AAAI CONF ARTIF INTE, P4170

[36]

Liu JC, 2021, Arxiv, DOI arXiv:2101.06804

[37] Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing [J].

Liu, Pengfei ;

Yuan, Weizhe ;

Fu, Jinlan ;

Jiang, Zhengbao ;

Hayashi, Hiroaki ;

Neubig, Graham .

ACM COMPUTING SURVEYS, 2023, 55 (09)

[38] OAG-BERT: Towards A Unified Backbone Language Model For Academic Knowledge Services [J].

Liu, Xiao ;

Yin, Da ;

Zheng, Jingnan ;

Zhang, Xingjian ;

Zhang, Peng ;

Yang, Hongxia ;

Dong, Yuxiao ;

Tang, Jie .

PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, :3418-3428

[39]

Ziegler DM, 2020, Arxiv, DOI [arXiv:1909.08593, 10.48550/arXiv.1909.08593]

[40]

Madotto A, 2020, Arxiv, DOI arXiv:2008.06239

← 1 2 3 4 5 6 7 8 →