abstraction-augmented-continual-learning

【数据与研究】Replace standard supervised fine-tuning loss with a dual-objective loss that jointly optimizes over both concrete instances and their abstract representations (entity-masked versions), eliminating need for replay buffers and improving cumulative accuracy by 2-5% on continual learning benchmarks. Use when streaming data contains latent relational stru…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准