Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes

ArXi:2603.27707v1 Announce Type: new Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of Low-Rank Adaptation (LoRA) in sequential transformer encoder fine-tuning with companion representation probes that test a frozen-backbone explanation of its robustness.