Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions

• URL: http://arxiv.org/abs/2509.25973v1
• Date: Tue, 30 Sep 2025 09:07:45 GMT
• Title: Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions
• Abstract summary: Language models trained on web-scale corpora risk memorizing and exposing sensitive information.<n>We propose Corrective Unlearning with Retrieved Exclusions (CURE), a novel unlearning framework.<n>CURE verifies model outputs for leakage and revises them into safe responses.
• Score: 49.55618517046225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often fails to eliminate the underlying knowledge and limits scalability. To address this, we propose Corrective Unlearning with Retrieved Exclusions (CURE), a novel unlearning framework that verifies model outputs for leakage and revises them into safe responses. Specifically, CURE employs a lightweight corrector that is applied to the original model to verify whether outputs contain target knowledge and to rewrite them if any leakage is detected. To efficiently handle large-scale unlearning requests, CURE retrieves unlearning targets that are relevant to the initial response and provides them as in-context references to the corrector for detection and conditional revision. By leveraging this retrieval augmentation, the corrector can adapt to new unlearning requests without additional training. Extensive evaluations demonstrate that CURE substantially reduces information leakage, even from indirect queries where prior works fall short, while maintaining response quality and general utility. Moreover, it demonstrates robustness under continual unlearning scenarios, making it practical for real-world applications.

Related papers

• Test-Time Unlearning via Sparse Autoencoder [55.4290003355764]
  We propose ARIA, a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state.<n>ARIA improves the forget-retain trade-off over weight-based baselines across both a thinking model and an instruction model.
  arXiv  Detail & Related papers  (2026-09-14T18:58:09Z)
• CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement [50.91045324738942]
  CLAIM is an uncertainty-driven framework for active clarification learning in open-domain settings.<n>We propose an entropy-driven synthetic data generation pipeline that integrates uncertainty estimation with semantic clustering and reasoning-based judgments.<n> Experimental results demonstrate that CLAIM can learn stable and generalizable clarification strategies without relying on manually labeled data.
  arXiv  Detail & Related papers  (2026-08-12T04:27:45Z)
• LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning [30.67510673327925]
  We introduce LACUNA: the first unlearning testbed with ground-truth parameter-level localization.<n>We show that LACUNA achieves strong erasure and robustness to resurfacing attacks, highlighting the importance of precise unlearning.
  arXiv  Detail & Related papers  (2026-07-02T17:59:52Z)
• Towards Reliable Testing of Machine Unlearning [9.923981046985771]
  Machine learning components are central to AI-infused software systems.<n>Machine unlearning is emerging as a practical alternative to full retraining.<n>This paper frames unlearning testing as a first-class software engineering problem.
  arXiv  Detail & Related papers  (2026-04-16T21:01:28Z)
• CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge [39.26757541186985]
  We propose Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge (CURaTE)<n>Our method begins by training a sentence embedding model on a dataset designed to enable the formation of sharp decision boundaries.<n>We show that even with such a simple approach, CURaTE achieve more effective forgetting than existing methods.
  arXiv  Detail & Related papers  (2026-04-16T05:49:10Z)
• The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning [54.67958855362658]
  We propose a dynamic framework that stress tests unlearning using complex structured queries.<n>Our approach first elicits knowledge from the target model (pre-unlearning) and constructs targeted probes, ranging from simple queries to multi-hop chains.<n>Our framework enables practical and scalable evaluation of unlearning methods without the need for manual construction of forget test sets.
  arXiv  Detail & Related papers  (2026-03-11T19:51:33Z)
• Suppression or Deletion: A Restoration-Based Representation-Level Analysis of Machine Unlearning [24.40457827994831]
  We propose a novel restoration-based analysis framework for machine unlearning.<n>Applying our framework to 12 major unlearning methods in image classification tasks, we find that most methods achieve high restoration rates.<n>We propose new evaluation guidelines that prioritize representation-level verification.
  arXiv  Detail & Related papers  (2026-02-18T07:46:30Z)
• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• Consistency-Aware Editing for Entity-level Unlearning in Language Models [53.522931419965424]
  We introduce a novel consistency-aware editing (CAE) framework for entity-level unlearning.<n>CAE aggregates a diverse set of prompts related to a target entity, including its attributes, relations, and adversarial paraphrases.<n>It then jointly learns a low-rank update guided by a consistency regularizer that aligns the editing directions across prompts.
  arXiv  Detail & Related papers  (2025-12-19T15:18:07Z)
• Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs [31.768387661474904]
  Unlearning in large language models (LLMs) involves precisely removing specific information from a pre-trained model.<n>This is crucial to ensure safety of LLMs by deleting private data or harmful knowledge acquired during pre-training.<n>We introduce JensUn, where we leverage the Jensen-Shannon Divergence as the training objective for both forget and retain sets.<n>In extensive experiments, JensUn achieves better forget-utility trade-off than competing methods, and even demonstrates strong resilience to benign relearning.
  arXiv  Detail & Related papers  (2025-09-02T20:38:53Z)
• SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning [1.3312007032203859]
  We present the first study of backdoor attacks in Federated Prompt Learning.<n>We show that when malicious clients inject visually imperceptible, learnable noise triggers into input images, the global prompt learner becomes vulnerable to targeted misclassification.<n>Motivated by this vulnerability, we propose SABRE-FL, a lightweight, modular defense that filters poisoned prompt updates using an embedding-space anomaly detector trained offline on out-of-distribution data.
  arXiv  Detail & Related papers  (2025-06-25T23:15:20Z)
• Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods [0.9999629695552196]
  We demonstrate that certain machine unlearning methods may fail under straightforward prompt attacks.<n>We systematically evaluate eight unlearning techniques across three model families using output-based, logit-based, and probe analysis.
  arXiv  Detail & Related papers  (2025-06-11T23:36:30Z)
• Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models [10.041289551532804]
  We introduce the concept of Robust Unlearning, ensuring models are indistinguishable from retraining and resistant to adversarial recovery.<n>To empirically evaluate whether unlearning techniques meet this security standard, we propose the Unlearning Mapping Attack (UMA)<n>UMA actively probes models for forgotten traces using adversarial queries.
  arXiv  Detail & Related papers  (2025-04-21T01:56:15Z)
• GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation [62.63014905981601]
  Refusal-Aware Instruction Tuning (RAIT) aims to enhance Large Language Models (LLMs) by improving their ability to refuse responses to questions beyond their knowledge.<n>Effective RAIT must address two key challenges: firstly, effectively reject unknown questions to minimize hallucinations; secondly, avoid over-refusal to ensure questions that can be correctly answered are not rejected.<n>GraIT employs gradient-driven sample selection to effectively minimize hallucinations and (2) introduces an adaptive weighting mechanism during fine-tuning to reduce the risk of over-refusal.
  arXiv  Detail & Related papers  (2025-02-09T14:11:30Z)
• What Really Matters for Learning-based LiDAR-Camera Calibration [50.2608502974106]
  This paper revisits the development of learning-based LiDAR-Camera calibration.<n>We identify the critical limitations of regression-based methods with the widely used data generation pipeline.<n>We also investigate how the input data format and preprocessing operations impact network performance.
  arXiv  Detail & Related papers  (2025-01-28T14:12:32Z)
• DeepNote: Note-Centric Deep Retrieval-Augmented Generation [72.70046559930555]
  Retrieval-Augmented Generation (RAG) mitigates factual errors and hallucinations in Large Language Models (LLMs) for question-answering (QA)<n>We develop DeepNote, an adaptive RAG framework that achieves in-depth and robust exploration of knowledge sources through note-centric adaptive retrieval.
  arXiv  Detail & Related papers  (2024-10-11T14:03:29Z)
• VERA: Validation and Enhancement for Retrieval Augmented systems [0.0]
  We propose textbfVERA (textbfValidation and textbfEnhancement for textbfRetrieval textbfAugmented systems), a system designed to evaluate and enhance the retrieved context before response generation. VERA employs an evaluator-cum-enhancer LLM that first checks if external retrieval is necessary, evaluates the relevance and redundancy of the retrieved context, and refines it to eliminate non-essential information.
  arXiv  Detail & Related papers  (2024-09-18T16:10:47Z)
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models [52.40798352740857]
  We introduce the Iterative Contrastive Unlearning (ICU) framework, which consists of three core components.<n>A Knowledge Unlearning Induction module targets specific knowledge for removal using an unlearning loss.<n>A Contrastive Learning Enhancement module preserves the model's expressive capabilities against the pure unlearning goal.<n>An Iterative Unlearning Refinement module dynamically adjusts the unlearning process through ongoing evaluation and updates.
  arXiv  Detail & Related papers  (2024-07-25T07:09:35Z)

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.