ExploreSelf: Fostering User-driven Exploration and Reflection on Personal Challenges with Adaptive Guidance by Large Language Models

2024-09-15

arXiv.org

AI Summary

Existing writing intervention systems employ static prompting paradigms, constraining users’ reflective flexibility and diminishing emotional expression and cognitive restructuring efficacy. To address this, we propose an LLM-driven adaptive reflection support system featuring a novel user-led, interruptible, and context-aware dynamic questioning mechanism. The system integrates real-time intent modeling, interactive dialogue management, and dynamic prompt engineering to facilitate autonomous exploration of stress experiences. In an exploratory study with 19 participants, the system significantly enhanced engagement and reflection depth; 87% reported gaining novel cognitive insights, empirically validating the effectiveness of adaptive guidance in promoting psychological adjustment. Our core contribution lies in transcending conventional static prompting frameworks—introducing a personalized, process-oriented reflection support paradigm that dynamically adapts to users’ evolving cognitive and affective states throughout the reflective journey.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Intelligent User Interfaces

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
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Expressing stressful experiences in words is proven to improve mental and physical health, but individuals often disengage with writing interventions as they struggle to organize their thoughts and emotions. Reflective prompts have been used to provide direction, and large language models (LLMs) have demonstrated the potential to provide tailored guidance. However, current systems often limit users' flexibility to direct their reflections. We thus present ExploreSelf, an LLM-driven application designed to empower users to control their reflective journey, providing adaptive support through dynamically generated questions. Through an exploratory study with 19 participants, we examine how participants explore and reflect on personal challenges using ExploreSelf. Our findings demonstrate that participants valued the flexible navigation of adaptive guidance to control their reflective journey, leading to deeper engagement and insight. Building on our findings, we discuss the implications of designing LLM-driven tools that facilitate user-driven and effective reflection of personal challenges.

Problem

• Enhancing personal reflection with adaptive guidance
• Empowering user control in reflective writing
• Facilitating deeper engagement in mental health interventions

Innovation

• Adaptive LLM guidance
• User-driven reflection control
• Dynamic question generation