Table of Contents
Fetching ...

ChatGPT or A Silent Everywhere Helper: A Survey of Large Language Models

Azim Akhtarshenas, Afshin Dini, Navid Ayoobi

TL;DR

This survey systematizes Large Language Models (LLMs) with a focus on ChatGPT, detailing architecture, training, evaluation, and broad-domain applications. It delivers resource-centric documentation of datasets, models, and benchmarks, and synthesizes insights on multimodal and domain-specific LLMs, including trends from the WACV LLVM-AD workshop. The authors identify gaps in prior work—particularly in resources, datasets, and ChatGPT-specific analysis—and propose future directions centered on alignment, efficiency, privacy, and governance. The study aims to aid researchers, developers, policymakers, educators, and industry stakeholders by clarifying capabilities, risks, and deployment considerations of LLMs in real-world settings.

Abstract

Large Language Models (LLMs) have revo lutionized natural language processing Natural Language Processing (NLP), with Chat Generative Pre-trained Transformer (ChatGPT) standing out as a notable exampledue to its advanced capabilities and widespread applications. This survey provides a comprehensive analysis of ChatGPT, exploring its architecture, training processes, and functionalities. We examine its integration into various domains across industries such as customer service, education, healthcare, and entertainment. A comparative analysis with other LLMs highlights ChatGPT's unique features and performance metrics. Regarding benchmarks, the paper examines ChatGPT's comparative performance against other LLMs and discusses potential risks such as misinformation, bias, and data privacy concerns. Additionally, we offer a number of figures and tables that outline the backdrop of the discussion, the main ideas of the article, the numerous LLM models, a thorough list of datasets used for pre-training, fine-tuning, and evaluation, as well as particular LLM applications with pertinent references. Finally, we identify future research directions and technological advancements, underscoring the evolving landscape of LLMs and their profound impact on artificial intelligence Artificial Intelligence (AI) and society.

ChatGPT or A Silent Everywhere Helper: A Survey of Large Language Models

TL;DR

This survey systematizes Large Language Models (LLMs) with a focus on ChatGPT, detailing architecture, training, evaluation, and broad-domain applications. It delivers resource-centric documentation of datasets, models, and benchmarks, and synthesizes insights on multimodal and domain-specific LLMs, including trends from the WACV LLVM-AD workshop. The authors identify gaps in prior work—particularly in resources, datasets, and ChatGPT-specific analysis—and propose future directions centered on alignment, efficiency, privacy, and governance. The study aims to aid researchers, developers, policymakers, educators, and industry stakeholders by clarifying capabilities, risks, and deployment considerations of LLMs in real-world settings.

Abstract

Large Language Models (LLMs) have revo lutionized natural language processing Natural Language Processing (NLP), with Chat Generative Pre-trained Transformer (ChatGPT) standing out as a notable exampledue to its advanced capabilities and widespread applications. This survey provides a comprehensive analysis of ChatGPT, exploring its architecture, training processes, and functionalities. We examine its integration into various domains across industries such as customer service, education, healthcare, and entertainment. A comparative analysis with other LLMs highlights ChatGPT's unique features and performance metrics. Regarding benchmarks, the paper examines ChatGPT's comparative performance against other LLMs and discusses potential risks such as misinformation, bias, and data privacy concerns. Additionally, we offer a number of figures and tables that outline the backdrop of the discussion, the main ideas of the article, the numerous LLM models, a thorough list of datasets used for pre-training, fine-tuning, and evaluation, as well as particular LLM applications with pertinent references. Finally, we identify future research directions and technological advancements, underscoring the evolving landscape of LLMs and their profound impact on artificial intelligence Artificial Intelligence (AI) and society.

Paper Structure

This paper contains 92 sections, 4 figures, 4 tables.

Figures (4)

  • Figure 1: Number of Published Papers on ChatGPT and LLM (2020-2024)
  • Figure 2: Overview of LLM usage in the future life
  • Figure 3: Update it based on context, make it smaller maybe, correct font.
  • Figure 4: Different LLM Models