"OpenBloom": A Question-Based LLM Tool to Support Stigma Reduction in Reproductive Well-Being

TL;DR

OpenBloom is an AI tool that transforms reproductive health articles into reflective questions to reduce stigma and promote inquiry-based learning, revealing design considerations and current limitations of LLMs in sensitive health education.

Contribution

The paper introduces OpenBloom, a novel LLM-based system for stigma-sensitive reproductive health education, and explores challenges and design principles for AI in sensitive health domains.

Findings

LLMs can generate culturally sensitive questions with empathetic framing.

Current LLM outputs tend to be superficial, focusing on rephrasing and recall.

Design considerations include inclusive language and explicit representation of marginalized identities.

Abstract

Reproductive well-being education remains widely stigmatized across diverse cultural contexts, constraining how individuals access and interpret reproductive health knowledge. We designed and evaluated OpenBloom, a stigma-sensitive, AI-mediated system that uses LLMs to transform reproductive health articles into reflective, question-based learning prompts. We employed OpenBloom as a design probe, aiming to explore the emerging challenges of reproductive well-being stigma through LLMs. Through surveys, semi-structured interviews, and focus group discussions, we examine how sociocultural stigma shapes participants' engagements with AI-generated questions and the opportunities of inquiry-based reproductive health education. Our findings identify key design considerations for stigma-sensitive LLM, including empathetic framing, inclusive language, values-based reflection, and explicit representation of marginalized identities. However, while current LLM outputs largely meet expectations for cultural sensitivity and non-offensiveness, they default to superficial rephrasing and factual recall rather than critical reflection. This guides well-being HCI design in sensitive health domains toward culturally grounded, participatory workflows.