背景(考古学)
计算机科学
数据科学
工作(物理)
工程类
地理
考古
机械工程
作者
Qingxiu Dong,Li Lei,Damai Dai,Ce Zheng,Zhiyong Wu,Baobao Chang,Xu Sun,Jingjing Xu,Li Lei,Zhifang Sui
出处
期刊:Cornell University - arXiv
日期:2023-01-01
被引量:134
标识
DOI:10.48550/arxiv.2301.00234
摘要
With the increasing ability of large language models (LLMs), in-context learning (ICL) has become a new paradigm for natural language processing (NLP), where LLMs make predictions only based on contexts augmented with a few examples. It has been a new trend to explore ICL to evaluate and extrapolate the ability of LLMs. In this paper, we aim to survey and summarize the progress and challenges of ICL. We first present a formal definition of ICL and clarify its correlation to related studies. Then, we organize and discuss advanced techniques, including training strategies, demonstration designing strategies, as well as related analysis. Finally, we discuss the challenges of ICL and provide potential directions for further research. We hope that our work can encourage more research on uncovering how ICL works and improving ICL.
科研通智能强力驱动
Strongly Powered by AbleSci AI