Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning

• URL: http://arxiv.org/abs/2605.16776v1
• Date: Sat, 16 May 2026 03:15:35 GMT
• Title: Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
• Abstract summary: Distinguishable Deletion ($mathrmD2$) is a paradigm that restricts the response distribution in the latent representation rather than specific tokens.<n>We introduce an energy index that quantifies the presence of knowledge and the separation between unlearned and retained content.<n>Experiments demonstrate that EUA significantly outperforms previous methods, indicating the superiority of $mathrmD2$.
• Score: 58.725080160369494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and Distinguishable Refusal (DR), which steers models away from using sensitive knowledge during inference. Despite rapid progress, KD-based unlearning struggles with biased deletion due to suppressing specific token sequences as a substitute for complete knowledge removal, whereas DR-based unlearning risks the re-emergence of harmful knowledge because the underlying knowledge remains intact. To address these issues, we propose Distinguishable Deletion ($\mathrm{D^2}$), a paradigm that restricts the response distribution in the latent representation rather than specific tokens to erase undesirable knowledge, while distinguishing it from retained knowledge, enabling a refusal mechanism to handle unlearned inputs safely and coherently. To implement $\mathrm{D^2}$, we introduce an energy index that quantifies the presence of knowledge and the separation between unlearned and retained content. Mathematical and empirical analyses show that energy is both accurate and efficient, enabling Energy-based Unlearning Alignment (EUA) to enforce energy-boundary unlearning during training and apply an energy-based refusal mechanism at inference. Extensive experiments demonstrate that EUA significantly outperforms previous methods, indicating the superiority of $\mathrm{D^2}$. Our code is available at https://github.com/Puning97/EUA-for-LLM-Unlearning.

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)
• Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs [54.96236442484317]
  We show that hazardous knowledge can be retained in the model and behaviorally gated by a privileged control token.<n>Our method, Token Inoculation, introduces a binding-and-branching approach.
  arXiv  Detail & Related papers  (2026-07-21T02:15:39Z)
• KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models [26.418820118903852]
  Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora.<n>LLMs unlearning is a promising technique to reduce risks associated with sensitive, copyrighted, or harmful content in training data.<n>We propose Knowledge Unlearning by Deviating representAtion (KUDA) to achieve effective unlearning at the knowledge level of LLMs.
  arXiv  Detail & Related papers  (2026-02-22T17:16:49Z)
• Auditing Language Model Unlearning via Information Decomposition [68.48660428111593]
  We introduce an interpretable, information-theoretic framework for auditing unlearning using Partial Information Decomposition (PID)<n>By comparing model representations before and after unlearning, we decompose the mutual information with the forgotten data into distinct components, formalizing the notions of unlearned and residual knowledge.<n>Our work introduces a principled, representation-level audit for unlearning, offering theoretical insight and actionable tools for safer deployment of language models.
  arXiv  Detail & Related papers  (2026-01-21T15:51:19Z)
• Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion [27.526437626781597]
  We propose Knowledge Density-Guided Unlearning via Blocks Reinsertion (KUnBR) for large language models.<n>KUnBR identifies layers with rich harmful knowledge and then thoroughly eliminates the harmful knowledge via re-insertion strategy.<n>Experiments conducted on several unlearning and general capability benchmarks demonstrate that KUnBR achieves state-of-the-art forgetting performance.
  arXiv  Detail & Related papers  (2025-11-11T14:12:43Z)
• Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions [49.55618517046225]
  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.
  arXiv  Detail & Related papers  (2025-09-30T09:07:45Z)
• Understanding the Dilemma of Unlearning for Large Language Models [50.54260066313032]
  Unlearning seeks to remove specific knowledge from large language models (LLMs)<n>We propose unPact, an interpretable framework for unlearning via prompt attribution and contribution tracking.
  arXiv  Detail & Related papers  (2025-09-29T12:15:19Z)
• Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models [9.719371187651591]
  Unlearning techniques suppress and leave the knowledge beneath the surface, thus making it retrievable with the right prompts.<n>We introduce a step-by-step reasoning-based black-box attack, Sleek, that systematically exposes unlearning failures.<n>Of the generated adversarial prompts, 62.5% successfully retrieved forgotten Harry Potter facts from WHP-unlearned Llama, while 50% exposed unfair suppression of retained knowledge.
  arXiv  Detail & Related papers  (2025-06-14T04:22:17Z)
• 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)
• Unlearning vs. Obfuscation: Are We Truly Removing Knowledge? [20.952703558942453]
  We formally distinguish unlearning from obfuscation and introduce a probing-based evaluation framework.<n>We propose DF-MCQ, a novel unlearning method that flattens the model predictive distribution over automatically generated multiple-choice questions.<n> Experimental results demonstrate that DF-MCQ achieves unlearning with over 90% refusal rate and a random choice-level uncertainty.
  arXiv  Detail & Related papers  (2025-05-05T14:21:08Z)
• UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI [50.61495097098296]
  We revisit the paradigm in which unlearning is used for Large Language Models (LLMs) We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context. We argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation.
  arXiv  Detail & Related papers  (2024-06-27T10:24:35Z)

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.