DiffLoRA: Differential Low-Rank Adapters for Large Language Models

• URL: http://arxiv.org/abs/2507.23588v1
• Date: Thu, 31 Jul 2025 14:24:59 GMT
• Title: DiffLoRA: Differential Low-Rank Adapters for Large Language Models
• Authors: Alexandre Misrahi, Nadezhda Chirkova, Maxime Louis, Vassilina Nikoulina,
• Abstract summary: We introduce DiffLoRA, a parameter-efficient adaptation of the differential attention mechanism, with low-rank adapters on both positive and negative attention terms.<n>We evaluate DiffLoRA across a broad range of NLP tasks, including general benchmarks, many-shot in-context learning, RAG, and long-context tests.
• Score: 59.58987161199141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Differential Transformer has recently been proposed to improve performance in Transformer models by canceling out noise through a denoiser attention mechanism. In this work, we introduce DiffLoRA, a parameter-efficient adaptation of the differential attention mechanism, with low-rank adapters on both positive and negative attention terms. This approach retains the efficiency of LoRA while aiming to benefit from the performance gains of differential attention. We evaluate DiffLoRA across a broad range of NLP tasks, including general benchmarks, many-shot in-context learning, RAG, and long-context tests. We observe that, although DiffLoRA falls short of other parameter-efficient fine-tuning methods in most evaluation tasks, it shows interesting results in certain domains (+11 pts on LoRA for HumanEval). We analyze the attention patterns post-finetuning to identify the reasons for this behavior.

Related papers

• Analyzing the Impact of Low-Rank Adaptation for Cross-Domain Few-Shot Object Detection in Aerial Images [9.869549856965259]
  This paper investigates the application of Low-Rank Adaptation (LoRA) to small models for cross-domain few-shot object detection in aerial images.<n>LoRA helps mitigate overfitting, making it a promising approach for resource-constrained settings.<n>Our results show that LoRA applied after an initial fine-tuning slightly improves performance in low-shot settings.
  arXiv  Detail & Related papers  (2025-04-08T14:10:39Z)
• BeamLoRA: Beam-Constraint Low-Rank Adaptation [51.52097743781401]
  Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.<n>We propose BeamLoRA, which conceptualizes each LoRA module as a beam where each rank naturally corresponds to a potential sub-solution.
  arXiv  Detail & Related papers  (2025-02-19T10:33:22Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning [9.91790333647256]
  Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods. We propose Mixture of Low-Rank Adaptation (MiLoRA), a novel and efficient LoRA variant. MiLoRA differs from previous MOE-style LoRA methods by considering each LoRA module as an expert and employing a prompt-aware routing mechanism.
  arXiv  Detail & Related papers  (2024-10-23T17:04:40Z)
• Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation [58.288682735160585]
  Low-Rank Adaptation (LoRA) is a popular technique for finetuning models. LoRA often under performs when compared to full- parameter fine-tuning. We present a framework that rigorously analyzes the adaptation rates of LoRA methods.
  arXiv  Detail & Related papers  (2024-10-10T18:51:53Z)
• ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models [8.251547772610301]
  We extend the methodology of low-rank adaptation (LoRA) to an innovative approach we call allocating low-rank adaptation (ALoRA) First, we propose a novel method, AB-LoRA, that can effectively estimate the importance score of each LoRA rank. Second, guided by AB-LoRA, we gradually prune abundant and negatively impacting LoRA ranks and allocate the pruned LoRA budgets to important Transformer modules needing higher ranks.
  arXiv  Detail & Related papers  (2024-03-24T15:09:55Z)
• MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning [71.50432879573614]
  Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional.<n>We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank.<n>Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks.
  arXiv  Detail & Related papers  (2024-02-27T07:14:12Z)
• LoRA Meets Dropout under a Unified Framework [38.5176197615878]
  Large language models (LLMs) have emerged as essential elements in numerous NLP applications. Various dropout methods, initially designed for full finetuning with all the parameters updated, alleviates overfitting associated with excessive parameter redundancy. We introduce a unified framework for a comprehensive investigation, which instantiates these methods based on dropping position, structural pattern and compensation measure.
  arXiv  Detail & Related papers  (2024-02-25T07:09:10Z)
• DoRA: Weight-Decomposed Low-Rank Adaptation [57.68678247436207]
  We introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA) DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning.
  arXiv  Detail & Related papers  (2024-02-14T17:59:34Z)
• Sparse Low-rank Adaptation of Pre-trained Language Models [79.74094517030035]
  We introduce sparse low-rank adaptation (SoRA) that enables dynamic adjustments to the intrinsic rank during the adaptation process. Our approach strengthens the representation power of LoRA by initializing it with a higher rank, while efficiently taming a temporarily increased number of parameters. Our experimental results demonstrate that SoRA can outperform other baselines even with 70% retained parameters and 70% training time.
  arXiv  Detail & Related papers  (2023-11-20T11:56:25Z)
• Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying [6.172790376076545]
  We introduce Tied-LoRA, a novel paradigm leveraging weight tying and selective training to enhance the parameter efficiency of Low-rank Adaptation (LoRA) Our exploration encompasses different plausible combinations of parameter training and freezing, coupled with weight tying, aimed at identifying the optimal trade-off between performance and the count of trainable parameters.
  arXiv  Detail & Related papers  (2023-11-16T05:29:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.