用提示词实现大模型持续学习，无需微调或新增参数。
Continual Learning Using Only Large Language Model Prompting
- 仅通过自然语言提示实现增量学习，不修改模型参数。
- 提出CIS方法，克服大模型输入长度限制，性能远超基线。
- 适合API可访问的大模型，部署简单、兼容性好。
我们提出CLOB，一种全新的持续学习范式，将大语言模型（LLM）视为黑箱，仅通过口头提示实现增量学习。CLOB不微调任何模型部分，也不向其添加可训练参数，特别适用于通过API访问的LLM。我们还提出一种新方法CIS，基于增量摘要技术，有效突破LLM的输入长度限制。实验表明，CIS在多个任务上显著优于现有基线。
原文摘要 · Abstract (English)
We introduce CLOB, a novel continual learning (CL) paradigm wherein a large language model (LLM) is regarded as a black box. Learning is done incrementally via only verbal prompting. CLOB does not fine-tune any part of the LLM or add any trainable parameters to it. It is particularly suitable for LLMs that are accessible via APIs. We also propose a new CL technique, called CIS, based on incremental summarization that also overcomes the LLM's input length limit. Experiments show CIS outperforms baselines by a very large margin.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。