Chatbot To Help Patients Understand Their Health
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915575802888192 |
|---|---|
| author | Jang, Won Seok Tran, Hieu Mistry, Manav Gandluri, SaiKiran Zhang, Yifan Sultana, Sharmin Kown, Sunjae Zhang, Yuan Yao, Zonghai Yu, Hong |
| author_facet | Jang, Won Seok Tran, Hieu Mistry, Manav Gandluri, SaiKiran Zhang, Yifan Sultana, Sharmin Kown, Sunjae Zhang, Yuan Yao, Zonghai Yu, Hong |
| contents | Patients must possess the knowledge necessary to actively participate in their care. We present NoteAid-Chatbot, a conversational AI that promotes patient understanding via a novel 'learning as conversation' framework, built on a multi-agent large language model (LLM) and reinforcement learning (RL) setup without human-labeled data. NoteAid-Chatbot was built on a lightweight LLaMA 3.2 3B model trained in two stages: 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05818 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chatbot To Help Patients Understand Their Health Jang, Won Seok Tran, Hieu Mistry, Manav Gandluri, SaiKiran Zhang, Yifan Sultana, Sharmin Kown, Sunjae Zhang, Yuan Yao, Zonghai Yu, Hong Artificial Intelligence Patients must possess the knowledge necessary to actively participate in their care. We present NoteAid-Chatbot, a conversational AI that promotes patient understanding via a novel 'learning as conversation' framework, built on a multi-agent large language model (LLM) and reinforcement learning (RL) setup without human-labeled data. NoteAid-Chatbot was built on a lightweight LLaMA 3.2 3B model trained in two stages: 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. |
| title | Chatbot To Help Patients Understand Their Health |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.05818 |