CASIA OpenIR  > 学术期刊  > Machine Intelligence Research
The Life Cycle of Knowledge in Big Language Models: A Survey
Boxi Cao1,3; Hongyu Lin1; Xianpei Han1,2; Le Sun1,2
发表期刊Machine Intelligence Research
ISSN2731-538X
2024
卷号21期号:2页码:217-238
摘要

Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowledge can be acquired, maintained, updated and used by language models. Despite the enormous amount of related studies, there is still a lack of a unified view of how knowledge circulates within language models throughout the learning, tuning, and application processes, which may prevent us from further understanding the connections between current progress or realizing existing limitations. In this survey, we revisit PLMs as knowledge-based systems by dividing the life circle of knowledge in PLMs into five critical periods, and investigating how knowledge circulates when it is built, maintained and used. To this end, we systematically review existing studies of each period of the knowledge life cycle, summarize the main challenges and current limitations, and discuss future directions.

关键词Pre-trained language model, knowledge acquisition, knowledge representation, knowledge probing, knowledge editing, knowledge application
DOI10.1007/s11633-023-1416-x
七大方向——子方向分类其他
国重实验室规划方向分类其他
是否有论文关联数据集需要存交
中文导读https://mp.weixin.qq.com/s/rKHHYu_CrXvFrcUSBqOf8w
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/56035
专题学术期刊_Machine Intelligence Research
作者单位1.Chinese Information Processing Laboratory, Beijing 100190, China
2.State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China
3.University of Chinese Academy of Sciences, Beijing 101408, China
推荐引用方式
GB/T 7714
Boxi Cao,Hongyu Lin,Xianpei Han,et al. The Life Cycle of Knowledge in Big Language Models: A Survey[J]. Machine Intelligence Research,2024,21(2):217-238.
APA Boxi Cao,Hongyu Lin,Xianpei Han,&Le Sun.(2024).The Life Cycle of Knowledge in Big Language Models: A Survey.Machine Intelligence Research,21(2),217-238.
MLA Boxi Cao,et al."The Life Cycle of Knowledge in Big Language Models: A Survey".Machine Intelligence Research 21.2(2024):217-238.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
MIR-2022-10-329.pdf(1430KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Boxi Cao]的文章
[Hongyu Lin]的文章
[Xianpei Han]的文章
百度学术
百度学术中相似的文章
[Boxi Cao]的文章
[Hongyu Lin]的文章
[Xianpei Han]的文章
必应学术
必应学术中相似的文章
[Boxi Cao]的文章
[Hongyu Lin]的文章
[Xianpei Han]的文章
相关权益政策
暂无数据
收藏/分享
文件名: MIR-2022-10-329.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。