Dynamic Prefix as Instructor for Incremental Named Entity Recognition: A Unified Seq2Seq Generation Framework

The Incremental Named Entity Recognition (INER) task aims to update a model to extract entities from an expanding set of entity type candidates due to concerns related to data privacy and scarcity.However, conventional sequence labeling approaches to INER often suffer from the catastrophic forgetting problem, which leads to the degradation of the model's performance on previously encountered entity types.In this paper, we formalize INER as a unified seq2seq generation task and propose a parameter-efficient dynamic prefix method.By employing the Dynamic Prefix as a task Instructor (DPI) to guide the generative model, our approach can preserve taskinvariant knowledge while adapting to new entities with minimal parameter updates, making it particularly effective in low-resource scenarios.Additionally, we introduce a generative label augmentation strategy with dual optimization objectives including a self-entropy loss and a task-aware similarity loss to enable optimal balance between stability and plasticity.Through extensive empirical evaluation on standard NER benchmarks, we demonstrate that our approach significantly outperforms existing methods, achieving up to 13.6% improvement in low-resource scenarios while maintaining strong performance on previously learned entity types.