由外部持续学习器辅助的上下文持续学习
In-context Continual Learning Assisted by an External Continual Learner
AI总结：
提出InCA方法，通过结合外部持续学习器（ECL）与上下文学习（ICL），为测试实例预选类别子集以限制提示长度，从而在不更新参数和避免灾难性遗忘的情况下实现可扩展的持续学习。
摘要：
现有的持续学习（CL）方法主要依赖于微调或适配大型语言模型（LLMs）。它们仍然面临灾难性遗忘（CF）的问题。目前很少有研究利用上下文学习（ICL）在不更新任何参数的情况下，利用LLMs内部的丰富知识来进行CL。然而，在ICL中逐步学习每个新任务需要将任务中每个类别的训练样本添加到提示中，这随着提示长度的增加阻碍了可扩展性。这个问题不仅会导致提示过长，超出底层LLM的输入token限制，还会因上下文过度延长而降低模型性能。为了解决这一问题，我们引入了InCA，这是一种将外部持续学习器（ECL）与ICL相结合的新方法，以实现无CF的可扩展CL。ECL通过增量构建，为每个测试实例预先选择一小部分可能的类别子集。通过将ICL提示限制为仅包含这些选定的类别，InCA在防止提示长度变得过长的同时，保持了高性能。实验结果表明，InCA显著优于现有的CL基线方法，取得了显著的性能提升。
英文摘要：
Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning (ICL) to leverage the extensive knowledge within LLMs for CL without updating any parameters. However, incrementally learning each new task in ICL necessitates adding training examples from each class of the task to the prompt, which hampers scalability as the prompt length increases. This issue not only leads to excessively long prompts that exceed the input token limit of the underlying LLM but also degrades the model's performance due to the overextended context. To address this, we introduce InCA, a novel approach that integrates an external continual learner (ECL) with ICL to enable scalable CL without CF. The ECL is built incrementally to pre-select a small subset of likely classes for each test instance. By restricting the ICL prompt to only these selected classes, InCA prevents prompt lengths from becoming excessively long, while maintaining high performance. Experimental results demonstrate that InCA significantly outperforms existing CL baselines, achieving substantial performance gains.
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。
