The Interaction Layer: An Exploration for Co-Designing User-LLM Interactions in Parental Wellbeing Support Systems

2024-11-02

arXiv.org

AI Summary

Low adoption of AI-based health support systems for new parents stems from insufficient explainability and reliability of current LLMs. Method: This study proposes a user-centered co-design methodology for LLM interaction layers, conducted via asynchronous remote community engagement involving parents and large multimodal models (LMMs). We introduce the novel “parent-role immersion dialogue rewriting” mechanism and formally define successful interactions along three dimensions: interpretability, controllability, and efficacy—yielding domain-specific LLM interaction design principles for parenting support. Contribution/Results: Integrating the CUQ (Contextual Usability Questionnaire) framework with the NurtureBot prototype, we achieve a CUQ score of 91.3/100, demonstrating significant improvements in user experience and interaction reliability. The results validate the effectiveness and innovation of this paradigm in enhancing trustworthiness and real-world adoption of AI-powered health support systems.

Technology Category

• Humans and AI: User Experience and Usability
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Parenting brings emotional and physical challenges, from balancing work, childcare, and finances to coping with exhaustion and limited personal time. Yet, one in three parents never seek support. AI systems potentially offer stigma-free, accessible, and affordable solutions. Yet, user adoption often fails due to issues with explainability and reliability. To see if these issues could be solved using a co-design approach, we developed and tested NurtureBot, a wellbeing support assistant for new parents. 32 parents co-designed the system through Asynchronous Remote Communities method, identifying the key challenge as achieving a"successful chat."Aspart of co-design, parents role-played as NurturBot, rewriting its dialogues to improve user understanding, control, and outcomes.The refined prototype evaluated by 32 initial and 46 new parents, showed improved user experience and usability, with final CUQ score of 91.3/100, demonstrating successful interaction patterns. Our process revealed useful interaction design lessons for effective AI parenting support.

Problem

• Addressing emotional and physical challenges in parenting through AI support.
• Improving user adoption by enhancing explainability and reliability of AI systems.
• Co-designing AI interactions to achieve successful and user-friendly parenting support.

Innovation

• Co-designed AI system using Asynchronous Remote Communities
• Implemented Interaction Layer for improved user experience
• Role-playing to refine dialogues for better understanding