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

Iraklis Premptis, Maria Lymperaiou, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Athanasios Voulodimos +1 more
3/4/2025
cs.CL

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss

88% match2025

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

88% match1 repo492025

UNLEARN Efficient Removal of Knowledge in Large Language Models

88% match2024

UniErase: Towards Balanced and Precise Unlearning in Language Models

87% match1 repo12025

ReLearn: Unlearning via Learning for Large Language Models

87% match1 repo492025

Test-Time Unlearning via Sparse Autoencoder

87% match2026

Cite this paper

@article{premptis2025ailsntua,
  title  = {AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking},
  author = {Iraklis Premptis and Maria Lymperaiou and Giorgos Filandrianos and Orfeas Menis Mastromichalakis and Athanasios Voulodimos and Giorgos Stamou},
  year   = {2025},
  eprint = {2503.02443},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.02443v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.02443.svg)](https://codeofpaper.com/paper/2503.02443)

Discussion