SOURCE-LINKED INTELLIGENCE

Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Privacy-preserving continual learning (PPCL) must reduce the reproduction of sensitive content while retaining useful knowledge across sequential tasks. Formal privacy guarantees characterize randomized mechanisms, whereas operational output control concerns whether a trained model selectively reduces the likelihood of sensitive content in its outputs. In this work, we investigate the latter together with continual-learning utility under realistic task evolution. Retention and privacy correction operate at different granularities: task acquisition requires broad preservation of current- and ol

Read original source ↗ Open in workspace

recordType

paper

region

Global