Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 6, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Multilingual Evaluation of a Large Language Model-Based Primary Care Chatbot.

Pei-Lun Chen, Amogh Ananda Rao, Sydney Pugh

Medrxiv : the Preprint Server for Health Sciences

|June 5, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

WATCH-SS: Developing a Trustworthy and Explainable Modular Framework for Detecting Cognitive Impairment from Spontaneous Speech.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026

Same author

Speaker Role Identification in Clinical Conversations.

medRxiv : the preprint server for health sciences·2025

Same author

WATCH-SS: Developing a Trustworthy and Explainable Modular Framework for Detecting Cognitive Impairment from Spontaneous Speech.

medRxiv : the preprint server for health sciences·2025

Same author

Observer: Creation of a Novel Multimodal Dataset for Outpatient Care Research.

medRxiv : the preprint server for health sciences·2025

Same author

MedVidDeID: Protecting privacy in clinical encounter video recordings.

Journal of biomedical informatics·2025

Same author

Helicobacter pylori-Associated Immune Thrombocytopenia: Diagnostic and Therapeutic Approach.

Annals of African medicine·2024

Same journal

Predicting Chemotherapy Response from Staging Laparoscopy Images.

medRxiv : the preprint server for health sciences·2026

Same journal

Development and External Validation of a Machine Learning Model for 10-Year Ischemic Stroke Risk Prediction in Diverse Populations.

medRxiv : the preprint server for health sciences·2026

Same journal

MCH-Guard: Multimodal Machine Learning Framework for Risk Stratification of Cerebral Microhemorrhage Risk in the Alzheimer's Disease Neuroimaging Initiative.

medRxiv : the preprint server for health sciences·2026

Same journal

Genetic and maternal environmental contributions to estimated fetal weight at 20 weeks gestation compared with birthweight.

medRxiv : the preprint server for health sciences·2026

Same journal

Better immediate declarative memory is associated with forgetting during locomotor adaptation in chronic stroke and in older adults.

medRxiv : the preprint server for health sciences·2026

Same journal

An empirical Bayes framework for burden and dispersion association tests helps prioritize rare variants associated with Alzheimer's disease.

medRxiv : the preprint server for health sciences·2026

See all related articles

Large language model (LLM) chatbots show promise for pre-visit planning. While Hindi interactions matched English, Mandarin and Spanish showed significant quality gaps, highlighting the need for multilingual validation in clinical AI.

Area of Science:

Clinical Informatics
Artificial Intelligence in Healthcare
Human-Computer Interaction

Background:

Pre-visit planning can reduce EHR burden and improve care.
Large language model (LLM) chatbots offer potential for clinical support.
English-centric LLM development raises concerns for multilingual clinical settings.

Purpose of the Study:

To evaluate the multilingual capabilities of PCP-Bot, an LLM-based clinical chatbot.
To assess performance disparities in Hindi, Mandarin, and Spanish compared to English.
To understand user experience and identify areas for improvement in non-English interactions.

Main Methods:

Mixed-methods study involving 31 bilingual participants (Hindi, Mandarin, Spanish).
Participants interacted with PCP-Bot across five synthetic cases in English and their second language.

More Related Videos

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

Related Experiment Videos

Last Updated: Jun 6, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

Evaluated usability, conversation quality, summary quality, trust, and workload via surveys and qualitative feedback.

Main Results:

Hindi interactions achieved parity with English in usability and conversation quality.
Mandarin showed usability parity but a conversation quality gap; Spanish had deficits in both.
Qualitative feedback noted issues like repetition and transcription errors in non-English interactions.

Conclusions:

LLM translation capabilities can support deployment beyond English with validation.
Performance varies across languages, necessitating careful evaluation for equitable clinical AI.
Addressing language-specific challenges is crucial for effective multilingual chatbot implementation.