AI RESEARCH
ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
arXiv CS.AI
•
ArXi:2605.27138v1 Announce Type: new Machine unlearning aims to remove the influence of specific data from trained language models. In real-world deployments, unlearning requests often arrive sequentially, which challenges existing fine-tuning-based methods: fine-tuning each request is costly, accumulates utility loss, and may cause cross-request interference.