Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being

2025-11-07

AI Summary

Existing large language models (LLMs) for adolescent mental health support suffer from insufficient personalization and detachment from real-life adolescent experiences. To address this, we employed participatory design—collaborating with adolescents, parents, and youth mental health practitioners—and innovatively introduced “co-created adolescent archetypes” as a design scaffold. This yielded three core principles: (1) individual-centered, context-sensitive responses; (2) explicit service boundary articulation; and (3) dialogue scaffolding that fosters reflection and autonomy. Guided by persuasive design theory and dialogue extraction techniques, we fine-tuned LLMs and optimized conversational interaction. The resulting system demonstrates significantly improved adaptability, trustworthiness, and community alignment among adolescents. Our work contributes a reusable design paradigm and practical implementation pathway for population-specific AI mental health systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Humans and AI: Intelligent User Interfaces
• Machine Learning: Large Multimodal Models (LMMs)

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
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Youth increasingly turn to large language models (LLMs) for mental well-being support, yet current personalization in LLMs can overlook the heterogeneous lived experiences shaping their needs. We conducted a participatory study with youth, parents, and youth care workers (N=38), using co-created youth personas as scaffolds, to elicit community perspectives on how LLMs can facilitate more meaningful personalization to support youth mental well-being. Analysis identified three themes: person-centered contextualization responsive to momentary needs, explicit boundaries around scope and offline referral, and dialogic scaffolding for reflection and autonomy. We mapped these themes to persuasive design features for task suggestions, social facilitation, and system trustworthiness, and created corresponding dialogue extracts to guide LLM fine-tuning. Our findings demonstrate how lived experience can be operationalized to inform design features in LLMs, which can enhance the alignment of LLM-based interventions with the realities of youth and their communities, contributing to more effectively personalized digital well-being tools.

Problem

• Personalization in LLMs overlooks diverse youth lived experiences
• LLMs lack meaningful personalization for youth mental well-being support
• Current LLM interventions misalign with youth realities and needs

Innovation

• Co-designed youth personas for personalization
• Fine-tuning LLMs with persuasive dialogue extracts
• Mapping lived experiences to design features