<ul><li>Existing continual learning (CL) methods rely on fine-tuning or adapting large language models (LLMs) but suffer from catastrophic forgetting (CF).</li><li>In-context learning (ICL) can leverage the extensive knowledge within LLMs for CL without updating any parameters.</li><li>However, scaling ICL becomes challenging as the prompt length increases and exceeds the input token limit.</li><li>To address this, the InCA approach integrates an external continual learner (ECL) with ICL, resulting in scalable CL without CF and achieving significant performance gains.</li></ul>

In-context Continual Learning Assisted by an External Continual Learner

Discover more