arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.14248cs.CL
收藏

从静态到动态:面向大型语言模型的持续学习框架

From Static to Dynamic: A Continual Learning Framework for Large Language Models

Nanyang Technological University(南洋理工大学);National University of Singapore(新加坡国立大学)

Mingzhe Du, Anh Tuan Luu, Bin Ji, See-kiong Ng

AI总结:

针对大型语言模型难以训练且难以持续吸收新知识导致输出不准确的问题,提出新型持续学习框架DynaMind,通过结合记忆机制与模块化算子增强推理,有效提升了模型输出准确性。

摘要:

大型语言模型(LLMs)庞大的参数量赋予了其卓越的能力,使其在各种自然语言处理任务中表现优异。然而,这种复杂性也带来了挑战,导致LLMs难以训练,并抑制了其持续吸收新知识的能力,这可能导致输出不准确。为缓解这些问题,本文提出了DynaMind,一种专为LLMs设计的新型持续学习框架。DynaMind结合记忆机制来吸收新知识,并利用模块化算子通过新吸收的知识增强模型推理过程,从而提高LLMs输出的准确性。基准实验证明了DynaMind在克服这些挑战方面的有效性。DynaMind的代码和演示可在GitHub获取:https://github.com/Elfsong/DynaMind。

英文摘要:

The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks. However, this complexity also presents challenges, making LLMs difficult to train and inhibiting their ability to continuously assimilate new knowledge, which may lead to inaccuracies in their outputs. To mitigate these issues, this paper presents DynaMind, a novel continual learning framework designed for LLMs. DynaMind incorporates memory mechanisms to assimilate new knowledge and modular operators to enhance the model inference process with the newly assimilated knowledge, consequently improving the accuracies of LLMs' outputs. Benchmark experiments demonstrate DynaMind's effectiveness in overcoming these challenges. The code and demo of DynaMind are available on GitHub: https://github.com/Elfsong/DynaMind.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑