mlsanityData to 14 Oct 2026

Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU

arXiv 2506.16548 ↗First posted 19 Jun 2025cs.LGcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their tendency to memorize training data raises concerns regarding privacy, copyright compliance, and security, particularly in cases involving Personally Identifiable Information (PII). Effective machine unlearning techniques are essential to mitigate these risks, yet existing methods remain underdeveloped for LLMs due to their open-ended output space. In this work, we apply the Adaptive Representation Misdirection Unlearning (RMU) technique to unlearn sensitive information from LLMs. Through extensive experiments, we analyze the effects of unlearning across different decoder layers to determine the most effective regions for sensitive information removal. Our technique ranked 4th on the official leaderboard of both 1B parameter and 7B parameter models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 14 of its 19 references that are in the map. First posted on arXiv 19 Jun 2025.

Builds on

14 of 19 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025LUME: LLM Unlearning with Multitask Evaluations20 Feb
  2. 2024Applying sparse autoencoders to unlearn knowledge in language models25 Oct
  3. 2024On Effects of Steering Latent Representation for Large Language Model Unlearning12 Aug
  4. 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct

Other references · 10

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  2. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  5. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
  6. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  7. 2024OLMo: Accelerating the Science of Language Modelscited by 613
  8. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 509
  9. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 372
  10. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Unlearning in LLMs: Methods, Evaluation, and Open Challenges
  2. 2024The Frontier of Data Erasure: Machine Unlearning for Large Language Models
  3. 2024Machine Unlearning in Large Language Models
  4. 2024A Closer Look at Machine Unlearning for Large Language Models
  5. 2024Towards Robust Evaluation of Unlearning in LLMs via Data Transformations
  6. 2024Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
  7. 2024Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models
  8. 2024Catastrophic Failure of LLM Unlearning via Quantization