Saved in:
Bibliographic Details
Main Authors: Jha, Smriti, Jain, Vidhi, Xu, Jianyu, Liu, Grace, Ramesh, Sowmya, Nagpal, Jitender, Chapman, Gretchen, Bellows, Benjamin, Goyal, Siddhartha, Singh, Aarti, Wilder, Bryan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.13168
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910051956948992
author Jha, Smriti
Jain, Vidhi
Xu, Jianyu
Liu, Grace
Ramesh, Sowmya
Nagpal, Jitender
Chapman, Gretchen
Bellows, Benjamin
Goyal, Siddhartha
Singh, Aarti
Wilder, Bryan
author_facet Jha, Smriti
Jain, Vidhi
Xu, Jianyu
Liu, Grace
Ramesh, Sowmya
Nagpal, Jitender
Chapman, Gretchen
Bellows, Benjamin
Goyal, Siddhartha
Singh, Aarti
Wilder, Bryan
contents The ability to provide trustworthy maternal health information using phone-based chatbots can have a significant impact, particularly in low-resource settings where users have low health literacy and limited access to care. However, deploying such systems is technically challenging: user queries are short, underspecified, and code-mixed across languages, answers require regional context-specific grounding, and partial or missing symptom context makes safe routing decisions difficult. We present a chatbot for maternal health in India developed through a partnership between academic researchers, a health tech company, a public health nonprofit, and a hospital. The system combines (1) stage-aware triage, routing high-risk queries to expert templates, (2) hybrid retrieval over curated maternal/newborn guidelines, and (3) evidence-conditioned generation from an LLM. Our core contribution is an evaluation workflow for high-stakes deployment under limited expert supervision. Targeting both component-level and end-to-end testing, we introduce: (i) a labeled triage benchmark (N=150) achieving 86.7% emergency recall, explicitly reporting the missed-emergency vs. over-escalation trade-off; (ii) a synthetic multi-evidence retrieval benchmark (N=100) with chunk-level evidence labels; (iii) LLM-as-judge comparison on real queries (N=781) using clinician-codesigned criteria; and (iv) expert validation. Our findings show that trustworthy medical assistants in multilingual, noisy settings require defense-in-depth design paired with multi-method evaluation, rather than any single model and evaluation method choice.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13168
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Developing and evaluating a chatbot to support maternal health care
Jha, Smriti
Jain, Vidhi
Xu, Jianyu
Liu, Grace
Ramesh, Sowmya
Nagpal, Jitender
Chapman, Gretchen
Bellows, Benjamin
Goyal, Siddhartha
Singh, Aarti
Wilder, Bryan
Artificial Intelligence
Computation and Language
Information Retrieval
The ability to provide trustworthy maternal health information using phone-based chatbots can have a significant impact, particularly in low-resource settings where users have low health literacy and limited access to care. However, deploying such systems is technically challenging: user queries are short, underspecified, and code-mixed across languages, answers require regional context-specific grounding, and partial or missing symptom context makes safe routing decisions difficult. We present a chatbot for maternal health in India developed through a partnership between academic researchers, a health tech company, a public health nonprofit, and a hospital. The system combines (1) stage-aware triage, routing high-risk queries to expert templates, (2) hybrid retrieval over curated maternal/newborn guidelines, and (3) evidence-conditioned generation from an LLM. Our core contribution is an evaluation workflow for high-stakes deployment under limited expert supervision. Targeting both component-level and end-to-end testing, we introduce: (i) a labeled triage benchmark (N=150) achieving 86.7% emergency recall, explicitly reporting the missed-emergency vs. over-escalation trade-off; (ii) a synthetic multi-evidence retrieval benchmark (N=100) with chunk-level evidence labels; (iii) LLM-as-judge comparison on real queries (N=781) using clinician-codesigned criteria; and (iv) expert validation. Our findings show that trustworthy medical assistants in multilingual, noisy settings require defense-in-depth design paired with multi-method evaluation, rather than any single model and evaluation method choice.
title Developing and evaluating a chatbot to support maternal health care
topic Artificial Intelligence
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2603.13168