@inproceedings{jang-etal-2025-chatbot,
title = "Chatbot To Help Patients Understand Their Health",
author = "Jang, Won Seok and
Tran, Hieu and
Mistry, Manav Shaileshkumar and
Gandluri, Sai Kiran and
Zhang, Yifan and
Sultana, Sharmin and
Kwon, Sunjae and
Zhang, Yuan and
Yao, Zonghai and
Yu, Hong",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.351/",
doi = "10.18653/v1/2025.findings-emnlp.351",
pages = "6598--6627",
ISBN = "979-8-89176-335-7",
abstract = "Patients must possess the knowledge necessary to actively participate in their care. To this end, we developed NoteAid-Chatbot, a conversational AI designed to help patients better understand their health through a novel framework of learning as conversation. We introduce a new learning paradigm that leverages a multi-agent large language model (LLM) and reinforcement learning (RL) framework{---}without relying on costly human-generated training data. Specifically, NoteAid-Chatbot was built on a lightweight 3-billion-parameter LLaMA 3.2 model using a two-stage training approach: initial supervised fine-tuning on conversational data synthetically generated using medical conversation strategies, followed by RL with rewards derived from patient understanding assessments in simulated hospital discharge scenarios. Our evaluation, which includes comprehensive human-aligned assessments and case studies, demonstrates that NoteAid-Chatbot exhibits key emergent behaviors critical for patient education{---}such as clarity, relevance, and structured dialogue{---}even though it received no explicit supervision for these attributes. Our results show that even simple Proximal Policy Optimization (PPO)-based reward modeling can successfully train lightweight, domain-specific chatbots to handle multi-turn interactions, incorporate diverse educational strategies, and meet nuanced communication objectives. Our Turing test demonstrates that NoteAid-Chatbot surpasses non-expert human. Although our current focus is on healthcare, the framework we present illustrates the feasibility and promise of applying low-cost, PPO-based RL to realistic, open-ended conversational domains{---}broadening the applicability of RL-based alignment methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jang-etal-2025-chatbot">
<titleInfo>
<title>Chatbot To Help Patients Understand Their Health</title>
</titleInfo>
<name type="personal">
<namePart type="given">Won</namePart>
<namePart type="given">Seok</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hieu</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manav</namePart>
<namePart type="given">Shaileshkumar</namePart>
<namePart type="family">Mistry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Kiran</namePart>
<namePart type="family">Gandluri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharmin</namePart>
<namePart type="family">Sultana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunjae</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zonghai</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Patients must possess the knowledge necessary to actively participate in their care. To this end, we developed NoteAid-Chatbot, a conversational AI designed to help patients better understand their health through a novel framework of learning as conversation. We introduce a new learning paradigm that leverages a multi-agent large language model (LLM) and reinforcement learning (RL) framework—without relying on costly human-generated training data. Specifically, NoteAid-Chatbot was built on a lightweight 3-billion-parameter LLaMA 3.2 model using a two-stage training approach: initial supervised fine-tuning on conversational data synthetically generated using medical conversation strategies, followed by RL with rewards derived from patient understanding assessments in simulated hospital discharge scenarios. Our evaluation, which includes comprehensive human-aligned assessments and case studies, demonstrates that NoteAid-Chatbot exhibits key emergent behaviors critical for patient education—such as clarity, relevance, and structured dialogue—even though it received no explicit supervision for these attributes. Our results show that even simple Proximal Policy Optimization (PPO)-based reward modeling can successfully train lightweight, domain-specific chatbots to handle multi-turn interactions, incorporate diverse educational strategies, and meet nuanced communication objectives. Our Turing test demonstrates that NoteAid-Chatbot surpasses non-expert human. Although our current focus is on healthcare, the framework we present illustrates the feasibility and promise of applying low-cost, PPO-based RL to realistic, open-ended conversational domains—broadening the applicability of RL-based alignment methods.</abstract>
<identifier type="citekey">jang-etal-2025-chatbot</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.351</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.351/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>6598</start>
<end>6627</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chatbot To Help Patients Understand Their Health
%A Jang, Won Seok
%A Tran, Hieu
%A Mistry, Manav Shaileshkumar
%A Gandluri, Sai Kiran
%A Zhang, Yifan
%A Sultana, Sharmin
%A Kwon, Sunjae
%A Zhang, Yuan
%A Yao, Zonghai
%A Yu, Hong
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F jang-etal-2025-chatbot
%X Patients must possess the knowledge necessary to actively participate in their care. To this end, we developed NoteAid-Chatbot, a conversational AI designed to help patients better understand their health through a novel framework of learning as conversation. We introduce a new learning paradigm that leverages a multi-agent large language model (LLM) and reinforcement learning (RL) framework—without relying on costly human-generated training data. Specifically, NoteAid-Chatbot was built on a lightweight 3-billion-parameter LLaMA 3.2 model using a two-stage training approach: initial supervised fine-tuning on conversational data synthetically generated using medical conversation strategies, followed by RL with rewards derived from patient understanding assessments in simulated hospital discharge scenarios. Our evaluation, which includes comprehensive human-aligned assessments and case studies, demonstrates that NoteAid-Chatbot exhibits key emergent behaviors critical for patient education—such as clarity, relevance, and structured dialogue—even though it received no explicit supervision for these attributes. Our results show that even simple Proximal Policy Optimization (PPO)-based reward modeling can successfully train lightweight, domain-specific chatbots to handle multi-turn interactions, incorporate diverse educational strategies, and meet nuanced communication objectives. Our Turing test demonstrates that NoteAid-Chatbot surpasses non-expert human. Although our current focus is on healthcare, the framework we present illustrates the feasibility and promise of applying low-cost, PPO-based RL to realistic, open-ended conversational domains—broadening the applicability of RL-based alignment methods.
%R 10.18653/v1/2025.findings-emnlp.351
%U https://aclanthology.org/2025.findings-emnlp.351/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.351
%P 6598-6627
Markdown (Informal)
[Chatbot To Help Patients Understand Their Health](https://aclanthology.org/2025.findings-emnlp.351/) (Jang et al., Findings 2025)
ACL
- Won Seok Jang, Hieu Tran, Manav Shaileshkumar Mistry, Sai Kiran Gandluri, Yifan Zhang, Sharmin Sultana, Sunjae Kwon, Yuan Zhang, Zonghai Yao, and Hong Yu. 2025. Chatbot To Help Patients Understand Their Health. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 6598–6627, Suzhou, China. Association for Computational Linguistics.