Before and After ChatGPT: Revisiting AI-Based Dialogue Systems for Emotional Support

2026-03-13

AI Summary

This study addresses the critical scarcity of psychological support resources by examining the evolution of AI-driven emotional support dialogue systems from 2020 to 2024. It presents the first systematic comparison of research paradigms, methodologies, and technical approaches before and after the widespread adoption of large language models (LLMs). Drawing on bibliometric analysis and qualitative review of publications indexed in Web of Science, Scopus, and ACM Digital Library, with a focus on the ESConv dataset and highly cited LLM-based studies, the work reveals a paradigm shift from task-specific architectures to general-purpose large models. The findings indicate that LLMs substantially enhance linguistic flexibility and generalization capabilities, yet simultaneously introduce new challenges concerning reliability and safety, thereby offering crucial insights for the future design of AI-enabled mental health support systems.

Technology Category

• Humans and AI: Emotional Intelligence
• Natural Language Processing: Conversational AI/Dialog Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• 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
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Mental health remains a major public health concern, while access to timely psychological support is often limited. AI-based dialogue systems have emerged as promising tools to address these barriers, and recent advances in large language models (LLMs) have significantly transformed this research area. However, a systematic understanding of this technological transition is still limited. This study reviews the technological evolution of AI-driven dialogue systems for mental health, focusing on the shift from task-specific deep learning models to LLM-based approaches. We conducted a bibliometric analysis and qualitative trend review of studies published between 2020 and May 2024 using Web of Science, Scopus, and the ACM Digital Library. The qualitative analysis compared research conducted before and after the widespread adoption of LLMs. Pre-LLM research was represented by highly cited studies and work based on the ESConv dataset, while post-LLM research included highly cited dialogue systems built on LLMs. A total of 146 studies met the inclusion criteria, showing a steady growth in publications over time. Before the widespread use of LLMs, empathetic response generation mainly relied on task-specific deep learning models. Highly cited and ESConv-based studies commonly focused on multi-task learning and the integration of external knowledge. In contrast, recent LLM-based dialogue systems demonstrate improved linguistic flexibility and generalization for emotional support. However, these systems also raise concerns related to reliability and safety in mental health applications. This review highlights the technological transition of AI-based dialogue systems for mental health in the LLM era. By identifying current research trends and limitations, the findings provide guidance for developing more effective and reliable AI-driven counseling systems.

Problem

• AI-based dialogue systems
• emotional support
• large language models
• mental health
• technological transition

Innovation

• large language models
• empathetic dialogue systems
• mental health support
• technological transition
• LLM-based counseling