A Complete Survey on LLM-based AI Chatbots

TL;DR

The paper surveys the evolution of LLM-based chatbots from early rule-based systems to modern transformer-enabled agents, covering foundations, architectures, and a broad spectrum of applications including education, research, and healthcare. It provides a detailed taxonomy of applications and challenges, categorized into technical, ethical, and misuse perspectives, with emphasis on data, knowledge recency, and content generation. Key technical topics include transformer architectures, in-context learning, chain-of-thought prompting, and RLHF, along with multimodal and web-enabled capabilities. The authors outline future directions focused on model compression, green AI, enhanced prompting, and rigorous ethical guidelines to ensure safe, reliable, and inclusive deployment across domains.

Abstract

The past few decades have witnessed an upsurge in data, forming the foundation for data-hungry, learning-based AI technology. Conversational agents, often referred to as AI chatbots, rely heavily on such data to train large language models (LLMs) and generate new content (knowledge) in response to user prompts. With the advent of OpenAI's ChatGPT, LLM-based chatbots have set new standards in the AI community. This paper presents a complete survey of the evolution and deployment of LLM-based chatbots in various sectors. We first summarize the development of foundational chatbots, followed by the evolution of LLMs, and then provide an overview of LLM-based chatbots currently in use and those in the development phase. Recognizing AI chatbots as tools for generating new knowledge, we explore their diverse applications across various industries. We then discuss the open challenges, considering how the data used to train the LLMs and the misuse of the generated knowledge can cause several issues. Finally, we explore the future outlook to augment their efficiency and reliability in numerous applications. By addressing key milestones and the present-day context of LLM-based chatbots, our survey invites readers to delve deeper into this realm, reflecting on how their next generation will reshape conversational AI.

Figures (10)

• Figure 1: Increase in data volume over the years WorldDataVolume.
• Figure 2: Google search interest over time GoogleTrends2024IoT.
• Figure 3: Survey outline.
• Figure 4: Pre-LLM chatbots meet LLMs.
• Figure 5: Pre-LLM chatbots.