mlsanityData to 7 Oct 2026

Towards Robust Evaluation of Unlearning in LLMs via Data Transformations

arXiv 2411.15477 ↗First posted 23 Nov 2024cs.CL cs.AI cs.CYcited by 19

On the map: LLM safety and security → Machine unlearning

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.

Key facts. Cited by 19 papers in the map (data through 7 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.

Builds on

26 of 38 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024Digital Forgetting in Large Language Models: A Survey of Unlearning Methods2 Apr
  2. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  3. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMs31 Oct
  4. 2023Model Sparsity Can Simplify Machine Unlearning11 Apr
  5. 2023Boundary Unlearning21 Mar
  6. 2022Evaluating Machine Unlearning via Epistemic Uncertainty23 Aug
  7. 2022Quark: Controllable Text Generation with Reinforced Unlearning26 May
  8. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  9. 2021Machine Unlearning of Features and Labels26 Aug

Other references · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  8. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  10. 2020Aligning AI With Shared Human Valuescited by 706
  11. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  12. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
5 more
  1. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  2. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 413
  3. 2023An Overview of Catastrophic AI Riskscited by 214
  4. 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 199
  5. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 10.

19 papers.

Sort:

By area:

  1. 2025Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Modelscited by 25
  2. 2025ReLearn: Unlearning via Learning for Large Language Modelscited by 20
  3. 2025SEPS: A Separability Measure for Robust Unlearning in LLMscited by 5
  4. 2025DUSK: Do Not Unlearn Shared Knowledgecited by 4
  5. 2025Investigating Symbolic Triggers of Hallucination in Gemma Models Across HaluEval and TruthfulQAcited by 3
  6. 2026To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansioncited by 3
  7. 2025A Survey on Unlearning in Large Language Modelscited by 2
  8. 2026CALIBURN: Self-Calibrated LLM Unlearning Alignmentcited by 2
  9. 2025Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removalcited by 1
  10. 2025SymLoc: Symbolic Localization of Hallucination across HaluEval and TruthfulQAcited by 1
  11. 2026Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluationcited by 1
  12. 2026OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolutioncited by 1
7 more
  1. 2026BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answeringcited by 1
  2. 2025Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Datacited by 0
  3. 2026Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Datacited by 0
  4. 2026Efficient Unlearning through Maximizing Relearning Convergence Delaycited by 0
  5. 2026Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Modelscited by 0
  6. 2026Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearningcited by 0
  7. 2026New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Modelscited by 0