# The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning

arXiv: https://arxiv.org/abs/2603.11266 · HTML: https://mlsanity.com/paper/2603.11266/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 34 of its 37 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 34)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Eight Methods to Evaluate Robust Unlearning in LLMs](https://mlsanity.com/paper/2402.16835/) (2024)
- [DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks](https://mlsanity.com/paper/2309.17167/) (2023)
- [Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference](https://mlsanity.com/paper/2406.08607/) (2024)
- [RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2406.10890/) (2024)
- [Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries](https://mlsanity.com/paper/2406.12775/) (2024)
- [Position: LLM Unlearning Benchmarks are Weak Measures of Progress](https://mlsanity.com/paper/2410.02879/) (2024)
- [Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions](https://mlsanity.com/paper/2307.03941/) (2023)
- [Soft Prompting for Unlearning in Large Language Models](https://mlsanity.com/paper/2406.12038/) (2024)
- [Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges](https://mlsanity.com/paper/2311.15766/) (2023)
- [Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models](https://mlsanity.com/paper/2409.13474/) (2024)
- [Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs](https://mlsanity.com/paper/2402.11199/) (2024)
- [Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?](https://mlsanity.com/paper/2411.16679/) (2024)
- [DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph](https://mlsanity.com/paper/2406.17271/) (2024)

## Built on by (most cited first, 1 of 1)

- [Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality](https://mlsanity.com/paper/2608.23020/) (2026)

## Abstract (arXiv)

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.