ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models
This work addresses the problem of efficient fine-tuning for AI practitioners, offering a novel method that improves expressivity and performance over existing approaches, though it is incremental in the context of parameter-efficient fine-tuning.
The paper tackles the challenge of efficiently adapting large language models to new domains by introducing ABBA, a parameter-efficient fine-tuning architecture that decouples updates from pre-trained weights, achieving state-of-the-art results on arithmetic and commonsense reasoning benchmarks with significant performance gains.
Large Language Models have demonstrated strong performance across a wide range of tasks, but adapting them efficiently to new domains remains a key challenge. Parameter-Efficient Fine-Tuning (PEFT) methods address this by introducing lightweight, trainable modules while keeping most pre-trained weights fixed. The prevailing approach, LoRA, models updates using a low-rank decomposition, but its expressivity is inherently constrained by the rank. Recent methods like HiRA aim to increase expressivity by incorporating a Hadamard product with the frozen weights, but still rely on the structure of the pre-trained model. We introduce ABBA, a new PEFT architecture that reparameterizes the update as a Hadamard product of two independently learnable low-rank matrices. In contrast to prior work, ABBA fully decouples the update from the pre-trained weights, enabling both components to be optimized freely. This leads to significantly higher expressivity under the same parameter budget, a property we validate through matrix reconstruction experiments. Empirically, ABBA achieves state-of-the-art results on arithmetic and commonsense reasoning benchmarks, consistently outperforming existing PEFT methods by a significant margin across multiple models. Our code is publicly available at: https://github.com/CERT-Lab/abba.