Scholarlink

Background <p>The performance of global large language models (LLMs), trained largely on Western data, for disease in other settings and languages is unknown. Taking myopia as an illustration, we evaluated the global versus Chinese-domain LLMs in addressing Chinese-specific myopia-related questions.</p> Methods <p>Global LLMs (ChatGPT-3.5, ChatGPT-4.0, Google Bard, Llama-2 7B Chat) and Chinese-domain LLMs (Huatuo-GPT, MedGPT, Ali Tongyi Qianwen, and Baidu ERNIE Bot, Baidu ERNIE 4.0) were included. All LLMs were prompted to address 39 Chinese-specific myopia queries across 10 domains. 3 myopia experts evaluated the accuracy of responses with a 3-point scale. “Good”-rating responses were further evaluated for comprehensiveness and empathy using a five-point scale. “Poor”-rating responses were further prompted for self-correction and re-analysis.</p> Results <p>The top 3 LLMs in accuracy were ChatGPT-3.5 (8.72 ± 0.75), Baidu ERNIE 4.0 (8.62 ± 0.62), and ChatGPT-4.0 (8.59 ± 0.93), with highest proportions of 94.8% “Good” responses. Top five LLMs with comprehensiveness were ChatGPT-3.5 (4.58 ± 0.42), ChatGPT-4.0 (4.56 ± 0.50), Baidu ERNIE 4.0 (4.44 ± 0.49), MedGPT (4.34 ± 0.59), and Baidu ERNIE Bot (4.22 ± 0.74) (all <i>p</i> ≥ 0.059, versus ChatGPT-3.5). While for empathy were ChatGPT-3.5 (4.75 ± 0.25), ChatGPT-4.0 (4.68 ± 0.32), MedGPT (4.50 ± 0.47), Baidu ERNIE Bot (4.42 ± 0.46), and Baidu ERNIE 4.0 (4.34 ± 0.64) (all <i>p</i> ≥ 0.052, versus ChatGPT-3.5). Baidu ERNIE 4.0 did not receive a “Poor” rating, while others demonstrated self-correction capabilities, showing enhancements ranging from 50% to 100%.</p> Conclusions <p>Global and Chinese-domain LLMs demonstrate effective performance in addressing Chinese-specific myopia-related queries. Global LLMs revealed optimal performance in Chinese-language settings despite primarily training with non-Chinese data and in English.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative performance analysis of global and chinese-domain large language models for myopia

  • 期刊论文

  • 发表日期：

    2025年4月13日

查看全文
  • Zehua Jiang,
  • Yueyuan Xu,
  • Zhi Wei Lim,
  • Ziyao Wang,
  • Yingxiang Han,
  • Samantha Min Er Yew,
  • Zhe Pan,
  • Qian Wang,
  • Gangyue Wu,
  • Tien Yin Wong,
  • Xiaofei Wang,
  • Yaxing Wang,
  • Yih Chung Tham

摘要

Background

The performance of global large language models (LLMs), trained largely on Western data, for disease in other settings and languages is unknown. Taking myopia as an illustration, we evaluated the global versus Chinese-domain LLMs in addressing Chinese-specific myopia-related questions.

Methods

Global LLMs (ChatGPT-3.5, ChatGPT-4.0, Google Bard, Llama-2 7B Chat) and Chinese-domain LLMs (Huatuo-GPT, MedGPT, Ali Tongyi Qianwen, and Baidu ERNIE Bot, Baidu ERNIE 4.0) were included. All LLMs were prompted to address 39 Chinese-specific myopia queries across 10 domains. 3 myopia experts evaluated the accuracy of responses with a 3-point scale. “Good”-rating responses were further evaluated for comprehensiveness and empathy using a five-point scale. “Poor”-rating responses were further prompted for self-correction and re-analysis.

Results

The top 3 LLMs in accuracy were ChatGPT-3.5 (8.72 ± 0.75), Baidu ERNIE 4.0 (8.62 ± 0.62), and ChatGPT-4.0 (8.59 ± 0.93), with highest proportions of 94.8% “Good” responses. Top five LLMs with comprehensiveness were ChatGPT-3.5 (4.58 ± 0.42), ChatGPT-4.0 (4.56 ± 0.50), Baidu ERNIE 4.0 (4.44 ± 0.49), MedGPT (4.34 ± 0.59), and Baidu ERNIE Bot (4.22 ± 0.74) (all p ≥ 0.059, versus ChatGPT-3.5). While for empathy were ChatGPT-3.5 (4.75 ± 0.25), ChatGPT-4.0 (4.68 ± 0.32), MedGPT (4.50 ± 0.47), Baidu ERNIE Bot (4.42 ± 0.46), and Baidu ERNIE 4.0 (4.34 ± 0.64) (all p ≥ 0.052, versus ChatGPT-3.5). Baidu ERNIE 4.0 did not receive a “Poor” rating, while others demonstrated self-correction capabilities, showing enhancements ranging from 50% to 100%.

Conclusions

Global and Chinese-domain LLMs demonstrate effective performance in addressing Chinese-specific myopia-related queries. Global LLMs revealed optimal performance in Chinese-language settings despite primarily training with non-Chinese data and in English.