Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning

• URL: http://arxiv.org/abs/2510.00761v3
• Date: Mon, 13 Oct 2025 12:38:53 GMT
• Title: Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
• Authors: Yicheng Lang, Yihua Zhang, Chongyu Fan, Changsheng Wang, Jinghan Jia, Sijia Liu,
• Abstract summary: Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model.<n>Recent findings reveal that unlearning manipulations such as weight quantization or fine-tuning can quickly neutralize the intended forgetting.
• Score: 25.53799024782883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving its utility on unrelated tasks. This paradigm has shown promise in addressing privacy and safety concerns. However, recent findings reveal that unlearning effects are often fragile: post-unlearning manipulations such as weight quantization or fine-tuning can quickly neutralize the intended forgetting. Prior efforts to improve robustness primarily reformulate unlearning objectives by explicitly assuming the role of vulnerability sources. In this work, we take a different perspective by investigating the role of the optimizer, independent of unlearning objectives and formulations, in shaping unlearning robustness. We show that the 'grade' of the optimizer, defined by the level of information it exploits, ranging from zeroth-order (gradient-free) to first-order (gradient-based) to second-order (Hessian-based), is tightly linked to the resilience of unlearning. Surprisingly, we find that downgrading the optimizer, such as using zeroth-order methods or compressed-gradient variants (e.g., gradient sign-based optimizers), often leads to stronger robustness. While these optimizers produce noisier and less precise updates, they encourage convergence to harder-to-disturb basins in the loss landscape, thereby resisting post-training perturbations. By connecting zeroth-order methods with randomized smoothing, we further highlight their natural advantage for robust unlearning. Motivated by these insights, we propose a hybrid optimizer that combines first-order and zeroth-order updates, preserving unlearning efficacy while enhancing robustness. Extensive experiments on the MUSE and WMDP benchmarks, across multiple LLM unlearning algorithms, validate that our approach achieves more resilient forgetting without sacrificing unlearning quality.

Related papers

• Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation [58.3773038915023]
  Continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge.<n>Most existing approaches treat continual learning as avoiding interference with past updates, rather than considering what properties make the current task-specific update naturally preserve previously acquired knowledge.<n>We address this problem using a projected first-order method compatible with standard deep-dots used in vision-language models.
  arXiv  Detail & Related papers  (2026-01-31T13:27:02Z)
• OFMU: Optimization-Driven Framework for Machine Unlearning [5.100622189286672]
  Large language models increasingly require the ability to unlearn specific knowledge, such as user requests, copyrighted materials, or outdated information.<n>We propose OFMU, a penalty-based bi-level optimization framework that explicitly prioritizes forgetting while preserving retention.<n>We show that OFMU consistently outperforms existing unlearning methods in both efficacy and retained utility.
  arXiv  Detail & Related papers  (2025-09-26T15:31:32Z)
• Optimizers Qualitatively Alter Solutions And We Should Leverage This [62.662640460717476]
  Deep Neural Networks (DNNs) can not guarantee convergence to a unique global minimum of the loss when using only local information, such as SGD.<n>We argue that the community should aim at understanding the biases of already existing methods, as well as aim to build new DNNs with the explicit intent of inducing certain properties of the solution.
  arXiv  Detail & Related papers  (2025-07-16T13:33:31Z)
• BLUR: A Bi-Level Optimization Approach for LLM Unlearning [105.98410883830596]
  We argue that it is important to model the hierarchical structure of the unlearning problem.<n>We propose a novel algorithm, termed Bi-Level UnleaRning (textttBLUR), which delivers superior performance.
  arXiv  Detail & Related papers  (2025-06-09T19:23:05Z)
• UniErase: Towards Balanced and Precise Unlearning in Language Models [69.04923022755547]
  Large language models (LLMs) require iterative updates to address the outdated information problem.<n>UniErase is a novel unlearning framework that demonstrates precision and balanced performances between knowledge unlearning and ability retaining.
  arXiv  Detail & Related papers  (2025-05-21T15:53:28Z)
• SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs [24.48560556882878]
  We introduce $textbfDynamic DAE Guardrails$ (DSG), a novel method for precision unlearning.<n>Our experiments show DSG substantially outperforms leading unlearning methods.
  arXiv  Detail & Related papers  (2025-04-11T01:24:03Z)
• Boosting Alignment for Post-Unlearning Text-to-Image Generative Models [55.82190434534429]
  Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data.<n>This often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.<n>We propose a framework that seeks an optimal model update at each unlearning iteration, ensuring monotonic improvement on both objectives.
  arXiv  Detail & Related papers  (2024-12-09T21:36:10Z)
• Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning [27.991291785091736]
  This work studies the problem of large language model (LLM) unlearning, aiming to remove unwanted data influences.<n>Despite the increasing demand for unlearning, a technically-grounded optimization framework is lacking.<n>We propose a simple yet effective unlearning optimization framework, called SimNPO, showing that simplicity' in removing the reliance on a reference model benefits unlearning.
  arXiv  Detail & Related papers  (2024-10-09T17:58:12Z)
• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models [19.015202590038996]
  We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models. We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
  arXiv  Detail & Related papers  (2024-08-20T09:36:04Z)
• Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs [25.91643745340183]
  Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora.<n>This poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods.<n>We propose Low-rank Knowledge Unlearning (LoKU), a novel framework that enables robust and efficient unlearning for LLMs.
  arXiv  Detail & Related papers  (2024-08-13T04:18:32Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models [12.45822383965784]
  We introduce UnDIAL (Unlearning via Self-Distillation on Adjusted Logits), a novel and robust unlearning method. Our approach leverages self-distillation to adjust logits and selectively reduce the influence of targeted tokens.
  arXiv  Detail & Related papers  (2024-02-15T16:21:14Z)

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.