Perfectly to a Tee: Understanding User Perceptions of Personalized LLM-Enhanced Narrative Interventions

TL;DR

This study explores how large language models can generate personalized narratives for mental health, showing they are perceived as relatable and effective in promoting reflection among young adults, with implications for digital interventions.

Contribution

It introduces a method for creating personalized, LLM-enhanced narratives for mental health, demonstrating their effectiveness and perceived authenticity compared to human-written stories.

Findings

Personalized stories were more relatable and better at conveying key messages.

LLM-generated stories promoted reflection and reduced negative beliefs.

Stories maintained authenticity comparable to human-written narratives.

Abstract

Stories about overcoming personal struggles can effectively illustrate the application of psychological theories in real life, yet they may fail to resonate with individuals' experiences. In this work, we employ large language models (LLMs) to create tailored narratives that acknowledge and address unique challenging thoughts and situations faced by individuals. Our study, involving 346 young adults across two settings, demonstrates that personalized LLM-enhanced stories were perceived to be better than human-written ones in conveying key takeaways, promoting reflection, and reducing belief in negative thoughts. These stories were not only seen as more relatable but also similarly authentic to human-written ones, highlighting the potential of LLMs in helping young adults manage their struggles. The findings of this work provide crucial design considerations for future narrative-based digital mental health interventions, such as the need to maintain relatability without veering into implausibility and refining the wording and tone of AI-enhanced content.