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

TL;DR

This study explores how to incorporate youth lived experiences into large language models to improve personalized mental health support, emphasizing community-driven design and ethical boundaries.

Contribution

It introduces a participatory co-design approach with youth and stakeholders to operationalize lived experience into LLM personalization features.

Findings

Identification of three key themes for personalization: contextualization, boundaries, and reflection.

Development of dialogue extracts to guide LLM fine-tuning for youth mental well-being.

Design features aligned with community perspectives to improve LLM trustworthiness and relevance.

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.