Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning

• URL: http://arxiv.org/abs/2609.00605v1
• Date: Tue, 01 Sep 2026 02:47:43 GMT
• Title: Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
• Abstract summary: We term this gap forget-set misalignment and identify two cases.<n>In Under Unlearning, the forget set omits memorized information and leakage persists.<n>In Out-of-Knowledge Unlearning, the algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility.<n>We propose a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge.
• Score: 9.140696856930457
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequently breaks in realistic privacy settings where the original training data is inaccessible. We term this gap forget-set misalignment and identify two cases. In Under Unlearning, the forget set omits memorized information and leakage persists. In Out-of-Knowledge Unlearning, the algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility. Using gradient-level analysis, we show these behaviors arise from misaligned unlearning targets rather than specific optimization choices. We then propose CONfession-to-Forget-Set (CONFS), a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge. Across synthetic, multimodal, and real-world benchmarks, CONFS approaches Gold-standard performance on several metrics and achieves a competitive forgetting-utility balance, while preserving utility better than other data-blind forget-set constructions.

Related papers

• Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem [16.147107064302435]
  We develop a protocol and training corpus that captures forget-retain structure for real-world factual domains.<n>We introduce JensUn++, an unlearning algorithm that achieves the best forget-retain utility trade-off across three LLMs.
  arXiv  Detail & Related papers  (2026-07-10T09:31:29Z)
• SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion [39.17638540496959]
  SHRED (Self-distillation via High-surprisal-only Retain-set-free Entropy Demotion) is a retain-set-free unlearning method built on a key insight.<n>High-information tokens concentrate the model's memorized knowledge, while low-information tokens reflect general language competence.<n> SHRED is robust against relearning attacks and membership-inference attacks, and it maintains stable utility even after many sequential unlearning runs.
  arXiv  Detail & Related papers  (2026-05-08T09:25:18Z)
• Nested Learning: The Illusion of Deep Learning Architectures [57.41377373511876]
  We present a new learning paradigm, called Nested Learning (NL), that coherently represents a machine learning model with a set of nested, multi-level, and/or parallel problems.<n>We show three core contributions: Expressive generalizations are in fact as generalizations with deep memory and/or more powerful learning rules.<n>We present a new continuum for memory system that generalizes the traditional viewpoint of long/short-term memory.
  arXiv  Detail & Related papers  (2025-12-31T07:59:43Z)
• Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning [49.274436951541425]
  Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information.<n>Existing unlearning methods fail to achieve benign forgetting because they often degrade the model's general image understanding performance.<n>We propose the Sculpted Memory Forgetting Adapter (SMFA), which confines forgetting to targeted memory regions while preserving overall capabilities.
  arXiv  Detail & Related papers  (2025-11-25T11:22:45Z)
• LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data [69.5099112089508]
  Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data.<n>This work presents the first study of unlearning under perturbed or low-fidelity forget data, referred to as noisy forget sets.<n>We find that unlearning remains surprisingly robust to perturbations, provided that core semantic signals are preserved.
  arXiv  Detail & Related papers  (2025-10-10T05:10:49Z)
• BLUR: A Bi-Level Optimization Approach for LLM Unlearning [100.90394814817965]
  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)
• GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection [36.38245533018162]
  Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains.<n>Existing unlearning efforts typically fine-tune the model with resources such as forget data, retain data, and a calibration model.<n>We propose Generation-time Unlearning via Adaptive Restriction and Detection (GUARD), a framework that enables dynamic unlearning during LLM generation.
  arXiv  Detail & Related papers  (2025-05-19T16:26:58Z)
• CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept [5.345828824625758]
  We propose a novel amortized unlearning approach using codebook features and Sparse Autoencoders (SAEs) By leveraging a bottleneck to decompose the activation space and regulate information flow, our method efficiently unlearns targeted information while preserving the model's performance on unrelated data.
  arXiv  Detail & Related papers  (2024-10-08T10:26:22Z)
• TOFU: A Task of Fictitious Unlearning for LLMs [99.92305790945507]
  Large language models trained on massive corpora of data from the web can reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training data, provides us with a way to protect private data after training. We present TOFU, a benchmark aimed at helping deepen our understanding of unlearning.
  arXiv  Detail & Related papers  (2024-01-11T18:57:12Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)

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.