Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being
This work tackles the challenge of improving personalized digital well-being tools for youth, though it is incremental as it builds on existing LLM personalization methods by incorporating community perspectives.
The study addressed the problem of personalization in large language models (LLMs) for youth mental well-being by conducting a participatory study with 38 participants to co-design features based on lived experiences, resulting in themes like person-centered contextualization and dialogic scaffolding that were mapped to persuasive design features for LLM fine-tuning.
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.