The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning

• URL: http://arxiv.org/abs/2603.11266v1
• Date: Wed, 11 Mar 2026 19:51:33 GMT
• Title: The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
• Abstract summary: We propose a dynamic framework that stress tests unlearning using complex structured queries.<n>Our approach first elicits knowledge from the target model (pre-unlearning) and constructs targeted probes, ranging from simple queries to multi-hop chains.<n>Our framework enables practical and scalable evaluation of unlearning methods without the need for manual construction of forget test sets.
• Score: 54.67958855362658
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as multi-hop reasoning and entity aliasing, can recover supposedly forgotten information. As a result, current evaluation metrics often create an illusion of effectiveness, failing to detect these vulnerabilities due to reliance on static, unstructured benchmarks. We propose a dynamic framework that stress tests unlearning robustness using complex structured queries. Our approach first elicits knowledge from the target model (pre-unlearning) and constructs targeted probes, ranging from simple queries to multi-hop chains, allowing precise control over query difficulty. Our experiments show that the framework (1) shows comparable coverage to existing benchmarks by automatically generating semantically equivalent Q&A probes, (2) aligns with prior evaluations, and (3) uncovers new unlearning failures missed by other benchmarks, particularly in multi-hop settings. Furthermore, activation analyses show that single-hop queries typically follow dominant computation pathways, which are more likely to be disrupted by unlearning methods. In contrast, multi-hop queries tend to use alternative pathways that often remain intact, explaining the brittleness of unlearning techniques in multi-hop settings. Our framework enables practical and scalable evaluation of unlearning methods without the need for manual construction of forget test sets, enabling easier adoption for real-world applications. We release the pip package and the code at https://sites.google.com/view/unlearningmirage/home.

Related papers

• Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness [9.988890658939471]
  Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not.<n>We introduce unlearning as a novel benchmark to understand robust LLM knowledge removal across diverse reasoning paths and recovery attacks.
  arXiv  Detail & Related papers  (2026-08-05T06:53:20Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• 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)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics [82.0813150432867]
  We introduce OpenUnlearning, a standardized framework for benchmarking large language models (LLMs) unlearning methods and metrics.<n>OpenUnlearning integrates 13 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)
• 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)
• Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning [38.03304773600225]
  Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. We propose MUNCH, a simple uncertainty-based approach that breaks down multi-hop queries into subquestions and leverages the uncertainty of the unlearned model in final decision-making.
  arXiv  Detail & Related papers  (2024-10-17T07:00:15Z)
• 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.