SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques

2024-10-17

arXiv.org

AI Summary

To address critical barriers in mental health care—including low service accessibility, pervasive stigma, and insufficient personalization—this paper introduces SouLLMate: a real-time, de-stigmatizing psychological support framework powered by an adaptive large language model (LLM). Methodologically, it integrates retrieval-augmented generation (RAG), conversational information extraction, and dynamic user profiling. Key innovations include Key Indicator Summarization (KIS), Proactive Questioning Strategy (PQS), and Stacked Multi-Model Reasoning (SMMR), augmented with domain-specific knowledge injection, chain-of-thought prompting, and a professionally annotated suicide-risk dataset. Experimental results demonstrate significant improvements in long-context reasoning accuracy and semantic coherence. SouLLMate achieves safe, usable, and interpretable performance in initial risk screening, proactive intervention, and personalized response generation—establishing a verifiable, AI-driven paradigm for scalable, ethical mental health support.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Mental health issues significantly impact individuals' daily lives, yet many do not receive the help they need even with available online resources. This study aims to provide diverse, accessible, stigma-free, personalized, and real-time mental health support through cutting-edge AI technologies. It makes the following contributions: (1) Conducting an extensive survey of recent mental health support methods to identify prevalent functionalities and unmet needs. (2) Introducing SouLLMate, an adaptive LLM-driven system that integrates LLM technologies, Chain, Retrieval-Augmented Generation (RAG), prompt engineering, and domain knowledge. This system offers advanced features such as Risk Detection and Proactive Guidance Dialogue, and utilizes RAG for personalized profile uploads and Conversational Information Extraction. (3) Developing novel evaluation approaches for preliminary assessments and risk detection via professionally annotated interview data and real-life suicide tendency data. (4) Proposing the Key Indicator Summarization (KIS), Proactive Questioning Strategy (PQS), and Stacked Multi-Model Reasoning (SMMR) methods to enhance model performance and usability through context-sensitive response adjustments, semantic coherence evaluations, and enhanced accuracy of long-context reasoning in language models. This study contributes to advancing mental health support technologies, potentially improving the accessibility and effectiveness of mental health care globally.

Problem

• Providing accessible personalized mental health support using AI
• Detecting mental health risks through advanced language model techniques
• Enhancing real-time mental health assistance with adaptive LLM technologies

Innovation

• Adaptive LLM-driven system with RAG
• Proactive guidance dialogue with risk detection
• Key indicator summarization for context-sensitive responses