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

arXiv: https://arxiv.org/abs/2603.27707 · HTML: https://mlsanity.com/paper/2603.27707/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.10512/) (2023)
- [Orthogonal Subspace Learning for Language Model Continual Learning](https://mlsanity.com/paper/2310.14152/) (2023)
- [InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning](https://mlsanity.com/paper/2404.00228/) (2024)
- [LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models](https://mlsanity.com/paper/2310.08659/) (2023)
- [LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation](https://mlsanity.com/paper/2504.07448/) (2025)
- [LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2503.18985/) (2025)
- [Subspace Geometry Governs Catastrophic Forgetting in Low-Rank Adaptation](https://mlsanity.com/paper/2603.02224/) (2026)

## Abstract (arXiv)

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. In five full-validation BERT-base reruns on an RTE->MRPC->CoLA->SST-2 sequence, full fine-tuning yields 19.9%+/-4.8% average forgetting, whereas standard LoRA (r=8, query/value modules) yields 0.6%+/-1.4% (paired t-test, p=0.002, Cohen's d_s=3.12). Task-level analyses confirm this reduction is not merely an aggregate effect. Secondary experiments on RoBERTa-base show the same pattern, and the strongest EWC baseline remains at 15.5%+/-1.4% forgetting. A six-task extension reveals that low average forgetting can hide strong task-level heterogeneity. Fine-grained freezing ablations show a marked forgetting drop once frozen parameters exceed roughly 95%, with classifier-only and shallow-adapter baselines approaching LoRA. Companion task-similarity probes in GPT-2 and RoBERTa show the same directional story: frozen-backbone regimes preserve higher inter-task similarity than full fine-tuning, gradual unfreezing weakens stability, and full fine-tuning exhibits its clearest divergence at the final transformer layer. These results support a restrained mechanistic interpretation: LoRA helps largely because backbone freezing preserves a more stable shared feature scaffold. We position standard LoRA as both a strong empirical baseline for sequential encoder adaptation and a useful probe of how selective plasticity shapes interference in transformer continual learning.