# Generative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study

arXiv: https://arxiv.org/abs/2604.07558 · HTML: https://mlsanity.com/paper/2604.07558/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 123 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset](https://mlsanity.com/paper/2403.09029/) (2024)
- [CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs](https://mlsanity.com/paper/2401.11314/) (2024)
- [Cognitive Reframing of Negative Thoughts through Human-Language Model Interaction](https://mlsanity.com/paper/2305.02466/) (2023)
- [PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement](https://mlsanity.com/paper/2403.04014/) (2024)
- [Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuring](https://mlsanity.com/paper/2310.15461/) (2023)
- [MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling](https://mlsanity.com/paper/2310.05231/) (2023)
- [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024)
- [ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles](https://mlsanity.com/paper/2310.15428/) (2023)
- [Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping](https://mlsanity.com/paper/2410.16232/) (2024)
- [Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Model](https://mlsanity.com/paper/2503.04084/) (2025)
- [ComPeer: A Generative Conversational Agent for Proactive Peer Support](https://mlsanity.com/paper/2407.18064/) (2024)
- [Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use](https://mlsanity.com/paper/2410.19155/) (2024)
- [MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention](https://mlsanity.com/paper/2309.16639/) (2023)
- [Understanding the Role of Large Language Models in Personalizing and Scaffolding Strategies to Combat Academic Procrastination](https://mlsanity.com/paper/2312.13581/) (2023)
- [The CoExplorer Technology Probe: A Generative AI-Powered Adaptive Interface to Support Intentionality in Planning and Running Video Meetings](https://mlsanity.com/paper/2405.18239/) (2024)
- [Investigating the Role of Situational Disruptors in Engagement with Digital Mental Health Tools](https://mlsanity.com/paper/2502.09776/) (2025)
- [User Perceptions of an LLM-Based Chatbot for Cognitive Reappraisal of Stress: Feasibility Study](https://mlsanity.com/paper/2601.00570/) (2026)

## Built on by (most cited first, 1 of 1)

- [Personalizing Personal Health Interfaces: Co-Design with Generative AI](https://mlsanity.com/paper/2609.15046/) (2026)

## Abstract (arXiv)

Digital mental health (DMH) tools have extensively explored personalization of interventions to users' needs and contexts. However, this personalization often targets what support is provided, not how it is experienced. Even well-matched content can fail when the interaction format misaligns with how someone can engage. We introduce generative experience as an approach to DMH support, where the intervention experience is composed at runtime. We instantiate this in GUIDE, a system that generates personalized intervention content and multimodal interaction structure through rubric-guided generation of modular components. In a preregistered study with N=237 participants, GUIDE significantly reduced stress (p=.02) and improved user experience (p=.04) compared to an LLM-based cognitive restructuring control. GUIDE also supported diverse forms of reflection and action through varied interaction flows, while revealing tensions around personalization across the interaction sequence. This work lays the foundation for interventions that dynamically shape how support is experienced and enacted in digital settings.