arXiv cs.CL· Hassan Saeed Hassan Albattra, Mazen Mohammed Bahgat, Rahatara Ferdousi, Hana Essam Sayed Ahmed Amrya, Mariam Mousa·· 12 小时前AI 评分29
HerHealthGPT：面向女性生殖健康的循证对话式 AI 系统
HerHealthGPT: An Evidence-Grounded Conversational AI System for Women's Reproductive Health Copy title
AI 导读
HerHealthGPT 是一个面向女性生殖健康的循证对话式 AI 系统，整合 RAG、上下文感知澄清与来源验证，在回答不完整健康提问前会先追问并核查证据。证据检索使关注类别准确率从 54.1% 提升至 59.3%，澄清路由在构造目标上达到 85.6% 召回率和 86.2% 特异度。30 人问卷研究中 83.3% 参与者偏好启用检索的配置，25 人认为追问相关问题。
正文
Abstract:"Why is my period late?" Sometimes, the most useful response begins with another question. Yet conversational AI systems may respond to incomplete health queries without seeking essential context or grounding their guidance in verifiable evidence. This paper introduces HerHealthGPT, an evidence-grounded conversational AI system designed to address these challenges in women's reproductive health. HerHealthGPT integrates retrieval-augmented generation (RAG), context-aware clarification, and source validation within an interactive web interface. Rather than responding immediately to incomplete queries, the system maintains conversational context, asks targeted follow-up questions, checks for premature conclusions, and grounds its responses in retrieved evidence. We evaluate the AI components using 540 English messages derived from 90 reproductive-health cases and conduct a prototype questionnaire study with 30 adults. Evidence retrieval improves concern-category accuracy from 54.1% to 59.3% compared with fine-tuning alone. The clarification router achieves 85.6% recall and 86.2% specificity on constructed targets. In the user study, 83.3% of participants preferred the retrieval-enabled configuration, while 25 of 30 considered its follow-up questions relevant. These findings suggest that integrating evidence retrieval with interactive clarification offers a promising approach to more transparent, context-aware reproductive-health information systems, while further clinical validation remains necessary.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.33931 [cs.CL] |
| (or arXiv:2610.33931v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33931 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hassan Albattra [view email]
[v1]
Sat, 24 Oct 2026 21:44:56 UTC (2,477 KB)
来源：arXiv cs.CL · arxiv.org