How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances

Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad, Jun Wang
10/11/2023
cs.CL

Official code: hyintell/awesome-refreshing-llms (135 stars, MIT, last commit 2023-12-12).

Abstract

Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment. Maintaining their up-to-date status is a pressing concern in the current era. This paper provides a comprehensive review of recent advances in aligning LLMs with the ever-changing world knowledge without re-training from scratch. We categorize research works systemically and provide in-depth comparisons and discussion. We also discuss existing challenges and highlight future directions to facilitate research in this field. We release the paper list at https://github.com/hyintell/awesome-refreshing-llms

View on arXivView PDF

Code Implementations(1)

hyintell/awesome-refreshing-llmsOfficial100%
MIT

EMNLP'23 survey: a curation of awesome papers and resources on refreshing large language models (LLMs) without expensive retraining.

13511Oct 8, 20232 years agoMIT
awesome-listcontinual-learningknowledge-editinglarge-language-modelsllm+10 more

Similar Papers

Defining a New NLP Playground

88% match2023

Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications

87% match2023

TigerBot: An Open Multilingual Multitask LLM

86% match1 repo2.3k2023

Eight Things to Know about Large Language Models

86% match2023

Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models

86% match2023

A Bibliometric Review of Large Language Models Research from 2017 to 2023

86% match2023

Cite this paper

@article{zhang2023large,
  title  = {How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances},
  author = {Zihan Zhang and Meng Fang and Ling Chen and Mohammad-Reza Namazi-Rad and Jun Wang},
  year   = {2023},
  eprint = {2310.07343},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.07343v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.07343.svg)](https://codeofpaper.com/paper/2310.07343)

Discussion