LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics

• URL: http://arxiv.org/abs/2510.07626v1
• Date: Wed, 08 Oct 2025 23:47:05 GMT
• Title: LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
• Authors: Chongyu Fan, Changsheng Wang, Yancheng Huang, Soumyadeep Pal, Sijia Liu,
• Abstract summary: We present a principled taxonomy of twelve recent stateful unlearning methods.<n>We revisit the evaluation of unlearning effectiveness (UE), utility retention (UT), and robustness (Rob)<n>Our analysis shows that current evaluations, dominated by multiple-choice question (MCQ) accuracy, offer only a narrow perspective.
• Score: 10.638045151201084
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model capabilities. Despite rapid progress over the past two years, research in LLM unlearning remains fragmented, with limited clarity on what constitutes effective unlearning and how it should be rigorously evaluated. In this work, we present a principled taxonomy of twelve recent stateful unlearning methods, grouped into three methodological families: divergence-driven optimization, representation misalignment, and rejection-based targeted unlearning. Building on this taxonomy, we revisit the evaluation of unlearning effectiveness (UE), utility retention (UT), and robustness (Rob), focusing on the WMDP benchmark. Our analysis shows that current evaluations, dominated by multiple-choice question (MCQ) accuracy, offer only a narrow perspective, often overstating success while overlooking the model's actual generation behavior. To address this gap, we introduce open question-answering (Open-QA) metrics that better capture generative performance and reveal the inherent UE-UT tradeoff across method families. Furthermore, we demonstrate that robustness requires finer-grained analysis: for example, vulnerabilities differ substantially between in-domain relearning and out-of-domain fine-tuning, even though both fall under model-level attacks. Through this study, we hope to deliver a full-stack revisit of LLM unlearning and actionable guidance for designing and evaluating future methods.

Related papers

• 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)
• OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics [101.78963920333342]
  We introduce OpenUnlearning, a standardized framework for benchmarking large language models (LLMs) unlearning methods and metrics.<n>OpenUnlearning integrates 9 unlearning algorithms and 16 diverse evaluations across 3 leading benchmarks.<n>We also benchmark diverse unlearning methods and provide a comparative analysis against an extensive evaluation suite.
  arXiv  Detail & Related papers  (2025-06-14T20:16:37Z)
• SoK: Machine Unlearning for Large Language Models [14.88062383081161]
  Large language model (LLM) unlearning has become a critical topic in machine learning.<n>We propose a new taxonomy based on the intention of unlearning.
  arXiv  Detail & Related papers  (2025-06-10T20:30:39Z)
• Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness [30.596695293390415]
  Interpolated Approximate Measurement (IAM) is a framework designed for unlearning inference.<n>IAM quantifies sample-level unlearning completeness by interpolating the model's generalization-fitting behavior gap on queried samples.<n>We apply IAM to recent approximate unlearning algorithms, revealing general risks of both over-unlearning and under-unlearning.
  arXiv  Detail & Related papers  (2025-06-06T14:22:18Z)
• A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models [35.893819613585315]
  This study investigates the machine unlearning techniques within the context of large language models (LLMs)<n>LLMs unlearning offers a principled approach to removing the influence of undesirable data from LLMs.<n>Despite growing research interest, there is no comprehensive survey that systematically organizes existing work and distills key insights.
  arXiv  Detail & Related papers  (2025-02-22T12:46:14Z)
• Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset [92.99416966226724]
  We introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms.<n>We apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels.<n>Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance.
  arXiv  Detail & Related papers  (2024-11-05T23:26:10Z)
• A Closer Look at Machine Unlearning for Large Language Models [46.245404272612795]
  Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns.<n>We discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches.
  arXiv  Detail & Related papers  (2024-10-10T16:56:05Z)
• 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)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• 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.