notesum.ai

Published at November 21

PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation

cs.CL

cs.AI

Released Date: November 21, 2024

Authors: Zhijie Bao¹, Qingyun Liu¹, Ying Guo², Zhengqiang Ye³, Jun Shen⁴, Shirong Xie³, Jiajie Peng⁵, Xuanjing Huang⁶, Zhongyu Wei⁷

Aff.: ¹School of Data Science, Fudan University, China; ²Shanghai Baoshan District Wusong Central Hospital, China; ³Eye & ENT Hospital of Fudan University, China; ⁴Zhongshan Hospital Wusong Branch, Fudan University, China; ⁵School of Computer Science, Northwestern Polytechnical University, China; ⁶School of Computer Science, Fudan University, China; ⁷Research Institute of Automatic and Complex Systems, Fudan University, China

Arxiv: http://arxiv.org/abs/2411.13902v1

$Refer to caption$

Method

Model

Accuracy

Overall

Score

Info

score

Average

Turn Number

Average

Turn Length

Directly Prompt

GPT-4o

0.717

3.83

2.16

3.54

207.98

Qwen2-7B

0.634

3.65

2.28

4.22

336.40

Llama3-8B

0.401

3.24

\ul2.65

4.44

678.14

HuatuoGPT2-13B

0.501

3.25

2.17

3.57

258.38

Fine-tuned

SF-ablated

nurse

\ul0.786

\ul3.92

2.20

\ul3.37

\ul202.55

PIORS-Nurse

0.822

4.01

3.01

3.22

139.54