mlsanityData to 7 Oct 2026

AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking

arXiv 2503.02443 ↗First posted 4 Mar 2025cs.CLcited by 6

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

The Unlearning Sensitive Content from Large Language Models task aims to remove targeted datapoints from trained models while minimally affecting their general knowledge. In our work, we leverage parameter-efficient, gradient-based unlearning using low-rank (LoRA) adaptation and layer-focused fine-tuning. To further enhance unlearning effectiveness, we employ data chunking, splitting forget data into disjoint partitions and merging them with cyclically sampled retain samples at a pre-defined ratio. Our task-agnostic method achieves an outstanding forget-retain balance, ranking first on leaderboards and significantly outperforming baselines and competing systems.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 13 of its 25 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

13 of 25 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025LUME: LLM Unlearning with Multitask Evaluations20 Feb
  2. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr
  3. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  4. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct

Other references · 9

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2020Extracting Training Data from Large Language Modelscited by 2,144
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  4. 2019Machine Unlearningcited by 1,020
  5. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  6. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  7. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  8. 2020Variational Bayesian Unlearningcited by 114
  9. 2024On Protecting the Data Privacy of Large Language Models (LLMs): A Surveycited by 91

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025Mitigating Biases in Language Models via Bias Unlearningcited by 6
  2. 2026Agentic Unlearning: When LLM Agent Meets Machine Unlearningcited by 6
  3. 2025Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocolscited by 4
  4. 2025Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearningcited by 1
  5. 2025Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Spacecited by 0
  6. 2025Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Datacited by 0