Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning

• URL: http://arxiv.org/abs/2606.10610v1
• Date: Tue, 09 Jun 2026 09:11:33 GMT
• Title: Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning
• Abstract summary: We propose a unified framework that brings adversarial training to PEFT.<n>This framework addresses the less explored intersection of adversarial training and parameter-efficient adaptation.<n>It makes PEFT deployments more reliable in real-world scenarios where data scarcity and linguistic variability often coexist.
• Score: 3.0344469521198003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become essential for adapting foundation models to downstream NLP tasks. However, current PEFT methods often struggle with robustness to noise and performance degradation on limited training data. We propose SDBN (Small Data Big Noise), a unified framework that brings adversarial training to PEFT - a combination that remains less studied in the PEFT setting despite its complementary strengths - to enhance model robustness and generalization, outperforming alternative approaches. We also introduce two variants of the method that use discrete uncertainty sets: SDBN-h, which enumerates character-level edits and selects worst-case variants using gradients, and SDBN-p, which uses LLM-generated variants for robust optimization in generative tasks. Experiments across multiple benchmarks reveal substantial improvements, particularly in low-resource settings and under both word-level and character-level corruptions. This framework addresses the less explored intersection of adversarial training and parameter-efficient adaptation, without introducing additional parameters or only modest computational overhead, making PEFT deployments more reliable in real-world scenarios where data scarcity and linguistic variability often coexist

Related papers

• Nonparametric Variational Differential Privacy via Embedding Parameter Clipping [7.242101014224729]
  We introduce a principled parameter clipping strategy to address privacy issues in variational language models.<n>Our findings show that the clipped model consistently achieves tighter RD bounds, implying stronger privacy.<n>This work presents a simple yet effective method for improving the privacy-utility trade-off in variational models, making them more robust and practical.
  arXiv  Detail & Related papers  (2026-03-10T12:34:03Z)
• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Adaptive Linear Path Model-Based Diffusion [52.84663832658799]
  We introduce Linear Path Model-Based Diffusion (LP-MBD), which replaces the variance-preserving schedule with a flow-matching linear probability path.<n>We also propose Adaptive LP-MBD (ALP-MBD), which leverages reinforcement learning to adjust diffusion steps and noise levels according to task complexity and environmental conditions.
  arXiv  Detail & Related papers  (2026-02-02T21:33:03Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• GRASP: GRouped Activation Shared Parameterization for Parameter-Efficient Fine-Tuning and Robust Inference of Transformers [12.475144734899674]
  We introduce GRASP, a lightweight PEFT framework that partitions the D-dimensional token representations of selected layers into K D groups and learns a shared scaling and shifting vector for each group.<n>We propose StochGRASP, which learns Gaussian distributions as perturbations to the pre-trained weights rather than deterministic values.<n>Under varying levels of noise, StochGRASP consistently outperforms deterministic variants, demonstrating its suitability for energy-efficient and noise-prone hardware platforms.
  arXiv  Detail & Related papers  (2025-12-03T22:17:05Z)
• A Bayesian Hybrid Parameter-Efficient Fine-Tuning Method for Large Language Models [6.289645856908972]
  Large Language Models (LLMs) have demonstrated transformative potential in reshaping the world.<n>As these models are pretrained on general corpora, they often require domain-specific fine-tuning to optimize performance in specialized business applications.<n>We propose a novel BH-PEFT method and dynamic fine-tuning approach that support uncertainty-aware and adaptive decision-making in real-world situations.
  arXiv  Detail & Related papers  (2025-07-31T01:20:20Z)
• Efficient Federated Class-Incremental Learning of Pre-Trained Models via Task-agnostic Low-rank Residual Adaptation [22.454292668849035]
  Federated Task-agnostic Low-rank Residual Adaptation (Fed-TaLoRA)<n>We develop a novel residual weight update mechanism that ensures accurate knowledge consolidation with minimal overhead.<n>Our methodological innovations are attributed to three key strategies: task-agnostic adaptation, post-aggregation model calibration, and strategic placement of LoRA modules.
  arXiv  Detail & Related papers  (2025-05-18T09:19:13Z)
• Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models [14.68920095399595]
  sparsity-based PEFT (SPEFT) introduces trainable sparse adaptations to the weight matrices in the model.<n>We conduct the first systematic evaluation of salience metrics for SPEFT, inspired by zero-cost NAS proxies.<n>We compare static and dynamic masking strategies, finding that static masking, which predetermines non-zero entries before training, delivers efficiency without sacrificing performance.
  arXiv  Detail & Related papers  (2024-12-18T04:14:35Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Learnable Bernoulli Dropout for Bayesian Deep Learning [53.79615543862426]
  Learnable Bernoulli dropout (LBD) is a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters. LBD leads to improved accuracy and uncertainty estimates in image classification and semantic segmentation.
  arXiv  Detail & Related papers  (2020-02-12T18:57:14Z)

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.