@inproceedings{das-biswas-etal-2026-ella,
    title = "{ELLA}: Efficient Lifelong Learning for Adapters in Large Language Models",
    author = "Das Biswas, Shristi  and
      Zhang, Yue  and
      Pal, Anwesan  and
      Bhargava, Radhika  and
      Roy, Kaushik",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.84/",
    pages = "1907--1924",
    ISBN = "979-8-89176-380-7",
    abstract = "Large Language Models (LLMs) suffer from severe catastrophic forgetting when adapted sequentially to new tasks in a continual learning (CL) setting. Existing approaches are fundamentally limited: replay-based methods are impractical and could potentially violate privacy, while strict orthogonality-based methods collapse under scale: each new task is projected onto an orthogonal complement, progressively reducing the residual degrees of freedom and eliminating forward transfer by forbidding overlap in shared representations. In this work, we introduce ELLA, a training framework built on the principle of selective subspace de-correlation. Rather than forbidding all overlap, ELLA explicitly characterizes the structure of past updates and penalizes alignments along their high-energy, task-specific directions, while preserving freedom in the low-energy residual subspaces to enable transfer. Formally, this is realized via a lightweight regularizer on a single aggregated update matrix. This mechanism is proven to be an anisotropic shrinkage operator that bounds interference, yielding a penalty that is both memory- and compute-constant regardless of task sequence length. ELLA requires no data replay, no architectural expansion, and negligible storage. Empirically, it achieves state-of-the-art CL performance on three popular benchmarks spanning both classification and generative tasks, with relative accuracy gains of up to 9.6{\%} and a $35\times$ smaller memory footprint. Furthermore, ELLA scales robustly across architectures and actively enhances the model{'}s zero-shot generalization performance on unseen tasks, establishing a principled and scalable solution for constructive lifelong LLM adaptation."
}