Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality

• URL: http://arxiv.org/abs/2608.23020v1
• Date: Mon, 24 Aug 2026 09:22:05 GMT
• Title: Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality
• Abstract summary: We present ADU, a training-based framework that shifts unlearning from token erasure to contextual attention-pathway decoupling.<n>ADU achieves the strongest aggregate performance among evaluated baselines on the TOFU and WMDP benchmarks.
• Score: 15.115560580671612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) require effective unlearning to address privacy regulations and safety concerns. However, achieving precise forgetting without compromising general utility remains challenging. Existing sequence- and token-level methods penalize target outputs without modeling their context-dependent retrieval paths, which can disrupt linguistic structure or suppress benign knowledge. We present ADU, a fine-grained, training-based framework that shifts unlearning from token erasure to contextual attention-pathway decoupling. Exploiting the functional distinction between local and global attention heads, ADU identifies preplan positions that retrieve persistent sensitive anchors and fixes their candidate paths under the original model. It then trains attention-projection adapters to suppress attention mass along these paths while preserving local-attention structure and retain-set language modeling. Post-training activation exchange tests whether the modified attention-output module transmits the learned forgetting effect. ADU achieves the strongest aggregate performance among evaluated baselines on the TOFU and WMDP benchmarks, including a Forget Quality of (0.93) on TOFU. It preserves 87--98% of model utility (92.9% on average versus 81.9% for baselines) while reducing side effects in benign contexts.

Related papers

• 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)
• Measuring the Depth of LLM Unlearning via Activation Patching [3.590648050085134]
  Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety.<n>Existing output-level metrics fail to detect when this knowledge remains recoverable from internal representations.<n>We propose the Unlearning Depth Score (UDS), a metric that quantifies the mechanistic depth of unlearning via activation patching.
  arXiv  Detail & Related papers  (2026-05-23T14:52:28Z)
• STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning [80.78140312980484]
  We propose language-driven stepwise trajectory redirection, termed as STRIDE.<n>We co-train a generator and a generative verifier using only outcome-based rewards, eliminating external annotations.<n> Experiments on diverse reasoning benchmarks show that STRIDE significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-13T11:04:31Z)
• MeGU: Machine-Guided Unlearning with Target Feature Disentanglement [73.49657372882082]
  We propose a novel framework that guides unlearning through concept-aware re-alignment.<n>MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.
  arXiv  Detail & Related papers  (2026-02-19T05:20:31Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• Representation-Aware Unlearning via Activation Signatures: From Suppression to Knowledge-Signature Erasure [2.0017902634527194]
  We introduce Knowledge Immunization Framework (KIF), a representation-aware architecture that distinguishes genuine erasure from obfuscation.<n>Our approach combines dynamic suppression of subject-specific representations with parameter-efficient adaptation, enabling durable unlearning without full model retraining.
  arXiv  Detail & Related papers  (2026-01-15T16:28:14Z)
• A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection [17.73056562717683]
  CoZAD is a novel zero-shot anomaly detection framework.<n>It integrates soft confident learning with meta-learning and contrastive feature representation.<n>We show it outperforms existing methods on 6 out of 7 industrial benchmarks.
  arXiv  Detail & Related papers  (2025-08-25T09:27:31Z)
• ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining [53.893792844055106]
  Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency.<n>We introduce Selective Efficient Language Modeling, a risk-aware algorithm that improves training efficiency and distributional robustness by performing online token-level batch selection.<n> Experiments on GPT-2 pretraining show that ESLM significantly reduces training FLOPs while maintaining or improving both perplexity and downstream performance compared to baselines.
  arXiv  Detail & Related papers  (2025-05-26T12:23:26Z)
• Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models [16.23854525619129]
  Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations.<n>We propose FocusVul, a model-agnostic framework that improves LM-based vulnerability detection by learning to select sensitive context.
  arXiv  Detail & Related papers  (2025-05-23T04:41:54Z)
• 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)
• DPP-Based Adversarial Prompt Searching for Lanugage Models [56.73828162194457]
  Auto-regressive Selective Replacement Ascent (ASRA) is a discrete optimization algorithm that selects prompts based on both quality and similarity with determinantal point process (DPP) Experimental results on six different pre-trained language models demonstrate the efficacy of ASRA for eliciting toxic content.
  arXiv  Detail & Related papers  (2024-03-01T05:28:06Z)
• A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation [53.8171136907856]
  We introduce a set of simple yet effective data augmentation strategies dubbed cutoff. cutoff relies on sampling consistency and thus adds little computational overhead. cutoff consistently outperforms adversarial training and achieves state-of-the-art results on the IWSLT2014 German-English dataset.
  arXiv  Detail & Related papers  (2020-09-29T07:08:35Z)

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.