"OpenBloom": A Stigma-Sensitive LLM Design Probe for Reproductive Well-Being

2026-06-13

AI Summary

This study addresses the challenges large language models (LLMs) face in sensitive health domains—such as reproductive health—where social stigma, contextual complexity, and insufficient user reflection hinder effective engagement. To tackle these issues, the authors propose and develop OpenBloom, a web-based LLM application that automatically transforms reproductive health articles into interrogative prompts designed to stimulate users’ exploration and critical reflection. Innovatively integrating feminist HCI, contestable design, and value-sensitive design frameworks, this work represents the first application of these approaches to LLM-driven health tools. An evaluation involving 34 participants across 136 interactions reveals that while current LLMs can generate non-offensive content, their outputs often remain superficial—limited to surface-level rephrasing or factual restatements—lacking the capacity to foster deeper reflective engagement.

Abstract

Ongoing discussions in Human-Computer Interaction(HCI) have examined the role of AI-based tools in health information seeking, particularly within sensitive domains such as reproductive health. We introduce "OpenBloom," a web application and an exploratory design probe that utilizes Large Language Models (LLMs) to turn reproductive health articles into question-based prompts to explore stigma around reproductive wellbeing. Through a survey study with 34 participants across their 136 interactions with OpenBloom, we explore how AI-generated question-based learning interacts with sociocultural stigma, contextual sensitivity, and reflexiveness. While current LLM outputs largely meet expectations for non-offensiveness, they default to superficial rephrasing or factual recall and lack critical reflections. We discuss implications for applying Feminist HCI, contestability, and value-sensitive AI frameworks to future LLM-mediated reproductive health technologies.

Problem

• reproductive health
• stigma
• Large Language Models
• sociocultural sensitivity
• reflexiveness

Innovation

• stigma-sensitive AI
• question-based prompting
• reproductive well-being
• Feminist HCI
• value-sensitive design