首页|期刊导航|计算机科学技术学报（英文版）|Exploring LLM-Based Data Synthesis Strategies for Aligning Medical Consultation Preferences

Exploring LLM-Based Data Synthesis Strategies for Aligning Medical Consultation Preferences

豆乘风张颖金芝焦文品赵海燕赵永强陶政为

计算机科学技术学报（英文版）2025，Vol.40Issue(6)：1485-1498,14.

计算机科学技术学报（英文版）2025，Vol.40Issue(6)：1485-1498,14.DOI:10.1007/s11390-025-4929-7

Exploring LLM-Based Data Synthesis Strategies for Aligning Medical Consultation Preferences

豆乘风 ¹张颖 ¹金芝 ¹焦文品 ¹赵海燕 ¹赵永强 ¹陶政为¹

作者信息

折叠

摘要

关键词

large language model(LLM)/medical dialogue/reinforcement learning from artificial intelligence feedback(RLAIF)/standardized patient testing

Key words

large language model(LLM)/medical dialogue/reinforcement learning from artificial intelligence feedback(RLAIF)/standardized patient testing

引用本文复制引用

豆乘风,张颖,金芝,焦文品,赵海燕,赵永强,陶政为..Exploring LLM-Based Data Synthesis Strategies for Aligning Medical Consultation Preferences[J].计算机科学技术学报（英文版）,2025,40(6):1485-1498,14.

基金项目

This work was supported by the National Key Research and Development Program of China under Grant No.2020AAA010-9400. （）

计算机科学技术学报（英文版）

ISSN：1000-9000

访问量2

下载量0

段落导航