# Towards Robust Evaluation of Unlearning in LLMs via Data Transformations

arXiv: https://arxiv.org/abs/2411.15477 · HTML: https://mlsanity.com/paper/2411.15477/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 23 Nov 2024.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [Identifying and Mitigating the Security Risks of Generative AI](https://mlsanity.com/paper/2308.14840/) (2023)
- [Digital Forgetting in Large Language Models: A Survey of Unlearning Methods](https://mlsanity.com/paper/2404.02062/) (2024)
- [Evaluating Machine Unlearning via Epistemic Uncertainty](https://mlsanity.com/paper/2208.10836/) (2022)

## Built on by (most cited first, 20 of 20)

- [Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2502.15910/) (2025)
- [ReLearn: Unlearning via Learning for Large Language Models](https://mlsanity.com/paper/2502.11190/) (2025)
- [SEPS: A Separability Measure for Robust Unlearning in LLMs](https://mlsanity.com/paper/2505.14832/) (2025)
- [DUSK: Do Not Unlearn Shared Knowledge](https://mlsanity.com/paper/2505.15209/) (2025)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQA](https://mlsanity.com/paper/2509.09715/) (2025)
- [To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion](https://mlsanity.com/paper/2607.23492/) (2026)
- [CALIBURN: Self-Calibrated LLM Unlearning Alignment](https://mlsanity.com/paper/2602.02824/) (2026)
- [Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal](https://mlsanity.com/paper/2502.18810/) (2025)
- [SymLoc: Symbolic Localization of Hallucination across HaluEval and TruthfulQA](https://mlsanity.com/paper/2511.14172/) (2025)
- [Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation](https://mlsanity.com/paper/2608.03791/) (2026)
- [OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution](https://mlsanity.com/paper/2609.06490/) (2026)
- [BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answering](https://mlsanity.com/paper/2609.06922/) (2026)
- [Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data](https://mlsanity.com/paper/2511.19498/) (2025)
- [Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Data](https://mlsanity.com/paper/2601.23153/) (2026)
- [Efficient Unlearning through Maximizing Relearning Convergence Delay](https://mlsanity.com/paper/2604.09391/) (2026)
- [Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models](https://mlsanity.com/paper/2605.20915/) (2026)
- [Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning](https://mlsanity.com/paper/2606.10989/) (2026)
- [New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models](https://mlsanity.com/paper/2609.11022/) (2026)
- [RA2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning](https://mlsanity.com/paper/2610.19385/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vast corpus of texts from various sources; despite the best efforts during the data pre-processing stage while training the LLMs, they may pick some undesirable information such as personally identifiable information (PII). Consequently, in recent times research in the area of Machine Unlearning (MUL) has become active, the main idea is to force LLMs to forget (unlearn) certain information (e.g., PII) without suffering from performance loss on regular tasks. In this work, we examine the robustness of the existing MUL techniques for their ability to enable leakage-proof forgetting in LLMs. In particular, we examine the effect of data transformation on forgetting, i.e., is an unlearned LLM able to recall forgotten information if there is a change in the format of the input? Our findings on the TOFU dataset highlight the necessity of using diverse data formats to quantify unlearning in LLMs more reliably.