AI RESEARCH
Understanding Generalization and Forgetting in In-Context Continual Learning
arXiv CS.LG
•
ArXi:2605.28705v1 Announce Type: new In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task settings, while real-world prompts often contain sequences of heterogeneous tasks, leaving a gap in understanding whether Large Language Models implicitly perform continual learning during inference.