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

2025-03-19

AI Summary

This study systematically evaluates the technical impact and societal applications of large language models (LLMs), such as ChatGPT, in natural language processing (NLP). Addressing the lack of full-cycle empirical data and integrated cross-dimensional risk analysis in prior work, we construct— for the first time—a unified dataset inventory spanning pretraining, fine-tuning, and evaluation stages, encompassing 30+ mainstream LLMs, 50+ benchmark datasets, and 8 application-domain case studies. We propose a multidimensional analytical framework integrating performance benchmarking, bias/privacy risk assessment, and interpretability evaluation. Through systematic literature review, experimental reproduction, and visualized comparative analysis, we identify three core challenges: insufficient model interpretability, difficulty in privacy alignment, and weak pedagogical adaptability. Based on these findings, we formulate an AI governance–oriented LLM development roadmap to guide responsible advancement.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Large Vision Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Analyzes ChatGPT's architecture, training, and functionalities
• Compares ChatGPT's performance with other large language models
• Examines risks like misinformation, bias, and data privacy

Innovation

• Comprehensive analysis of ChatGPT architecture
• Integration into diverse industry domains
• Comparative performance against other LLMs