Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning

• URL: http://arxiv.org/abs/2608.11408v1
• Date: Tue, 11 Aug 2026 20:16:20 GMT
• Title: Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning
• Abstract summary: J-Access is an inference-time audit that measures how often target concepts remain accessible along the model's output pathway.<n>We audit 398 public unlearned models spanning eight unlearning methods.
• Score: 57.920153607557744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prior white-box studies show that large language models can retain latent traces of target knowledge after unlearning, even when the knowledge is no longer expressed in their outputs. However, existing audits remain limited to one-off diagnostics: it is unclear whether these residual signals can predict future recovery under continued training or serve as reliable optimization targets. Resolving this gap is essential to determine whether internal auditing can move beyond post-hoc evaluation toward proactive risk monitoring and safer unlearning. We propose J-Access, an inference-time audit that uses the Jacobian lens to map intermediate representations into vocabulary space and measures how often target concepts remain accessible along the model's output pathway. We hypothesize that residual accessibility reflects recovery susceptibility: knowledge that remains closer to the output pathway requires less fine-tuning to restore, leading to faster recovery. We audit 398 public unlearned models spanning eight unlearning methods. We find that: (1) most unlearned models retain access above the retain-only gold level; (2) pre-attack accessibility predicts recovery speed and extent at the model level, but cannot identify which specific facts will be recovered; and (3) directly minimizing J-Access does not promote genuine deletion. Instead, the model learns to hide knowledge from the audit, producing lower audit scores but greater post-attack recovery. These findings position J-Access as a model-level diagnostic for assessing residual susceptibility in unlearned models. We argue internal audits should serve as an independent diagnostic dimension in unlearning evaluation, and should not be converted into optimization targets without validation.

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)
• SoK: Unlearnability and Unlearning for Model Dememorization [19.145486704492324]
  We present the first integrated analysis of model dememorization approaches leveraging unlearnability and unlearning.<n>Our contributions are threefold: (i) a unified taxonomy of unlearnability and scalable unlearning methods; (ii) an empirical evaluation revealing the robustness, interplay, and shallow dememorization of leading methods; and (iii) the first theoretical guarantee on dememorization depth for models processed through certified unlearning.
  arXiv  Detail & Related papers  (2026-05-12T06:17:13Z)
• REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs [0.1784233255402269]
  Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining.<n>We propose REMIND, a novel evaluation method aiming to detect the subtle remaining influence of unlearned data.<n>We show that unlearned data yield flatter, less steep loss landscapes, while retained or unrelated data exhibit sharper, more volatile patterns.
  arXiv  Detail & Related papers  (2025-11-06T09:58:19Z)
• Probing Knowledge Holes in Unlearned LLMs [23.377732810945172]
  Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training.<n>We find that unlearning may inadvertently create knowledge holes'' -- unintended losses of benign knowledge that standard benchmarks fail to capture.<n>We propose a test case generation framework that explores both immediate neighbors of unlearned content and broader areas of potential failures.
  arXiv  Detail & Related papers  (2025-10-27T03:11:53Z)
• Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check [60.77691669644931]
  We propose Functional Alignment for Distributional Equivalence (FADE), a novel metric that measures distributional similarity between unlearned and reference models.<n>We show that FADE captures functional alignment across the entire output distribution, providing a principled assessment of genuine unlearning.<n>These findings expose fundamental gaps in current evaluation practices and demonstrate that FADE provides a more robust foundation for developing and assessing truly effective unlearning methods.
  arXiv  Detail & Related papers  (2025-10-14T20:50:30Z)
• 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)
• 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)
• Existing Large Language Model Unlearning Evaluations Are Inconclusive [105.55899615056573]
  We show that some evaluations introduce substantial new information into the model, potentially masking true unlearning performance.<n>We demonstrate that evaluation outcomes vary significantly across tasks, undermining the generalizability of current evaluation routines.<n>We propose two principles for future unlearning evaluations: minimal information injection and downstream task awareness.
  arXiv  Detail & Related papers  (2025-05-31T19:43:00Z)
• 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)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• 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)

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.