A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage

Обзор больших языковых моделей: приложения, проблемы, ограничения и практическое применение
Seyedali Mirjalili, Mubarak Shah, Amgad Muneer, Rizwan Qureshi, Muhammad Usman Hadi, Syed Zohaib Hassan, Maged Shoman, Jia Wu, Abbas Shah, Qasem Al-Tashi, Naveed Akhtar, qasem al tashi, Muhammad Bilal Shaikh, Muhammad Irfan, Anas Zafar, Syed Zohaib Hassan, Maged Shoman
2023-07-10

generative pre-trained transformerslarge language modelsmachine translationmodel biasnatural language processing
Within the vast expanse of computerized language processing, a revolutionary entity known as Large Language Models (LLMs) has emerged, wielding immense power in its capacity to comprehend intricate linguistic patterns and conjure coherent and contextually fitting responses. Large language models (LLMs) are a type of artificial intelligence (AI) that have emerged as powerful tools for a wide range of tasks, including natural language processing (NLP), machine translation, and question-answering. This survey paper provides a comprehensive overview of LLMs, including their history, architecture, training methods, applications, and challenges. The paper begins by discussing the fundamental concepts of generative AI and the architecture of generative pre- trained transformers (GPT). It then provides an overview of the history of LLMs, their evolution over time, and the different training methods that have been used to train them. The paper then discusses the wide range of applications of LLMs, including medical, education, finance, and engineering. It also discusses how LLMs are shaping the future of AI and how they can be used to solve real-world problems. The paper then discusses the challenges associated with deploying LLMs in real-world scenarios, including ethical considerations, model biases, interpretability, and computational resource requirements. It also highlights techniques for enhancing the robustness and controllability of LLMs, and addressing bias, fairness, and generation quality issues. Finally, the paper concludes by highlighting the future of LLM research and the challenges that need to be addressed in order to make LLMs more reliable and useful. This survey paper is intended to provide researchers, practitioners, and enthusiasts with a comprehensive understanding of LLMs, their evolution, applications, and challenges. By consolidating the state-of-the-art knowledge in the field, this survey serves as a valuable resource for further advancements in the development and utilization of LLMs for a wide range of real-world applications. The GitHub repo for this project is available at https://github.com/anas-zafar/LLM-Survey
1
Future LLM research must address reliability and usefulness to enable broader real-world problem solving.
2
LLMs support diverse applications across natural language processing, machine translation, question answering, medicine, education, finance, and engineering.
3
Real-world LLM deployment faces ethical, bias, interpretability, and computational-resource challenges.
4
The survey highlights techniques for improving LLM robustness, controllability, fairness, bias mitigation, and generation quality.
5
The survey reviews large language models’ history, architectures, and training methods, including generative AI and GPT-based transformers.

Large Language Models (LLMs)

The history, architectures, training methods, applications, deployment challenges, limitations, and techniques for improving the robustness, controllability, fairness, interpretability, and generation quality of LLMs

Publication Details
Publication Date
2023-07-10
Journal
Publisher
ISSN
Cited by
785
Access Type
Author Information
Authors
Seyedali Mirjalili
Mubarak Shah
Amgad Muneer
Rizwan Qureshi
Muhammad Usman Hadi
Syed Zohaib Hassan
Maged Shoman
Jia Wu
Abbas Shah
Qasem Al-Tashi
Naveed Akhtar
qasem al tashi
Muhammad Bilal Shaikh
Muhammad Irfan
Anas Zafar
Syed Zohaib Hassan
Maged Shoman
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%