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

Source: [AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking](<https://www.sota2.com/research/paper/68fa7a561e209131cea82962>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:18:10.000Z

Authors: Iraklis Premptis, Maria Lymperaiou, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Athanasios Voulodimos, Giorgos Stamou

Published: 2025-03-04T09:39:09.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Machine Unlearning on MedMCQA QF=1000](<https://www.sota2.com/research/sota/machine-unlearning-on-medmcqa-qf-1000.md>): Machine Unlearning; MedMCQA QF=1000; Forget Accuracy: 90.

- [Machine Unlearning on MedQA QF=100](<https://www.sota2.com/research/sota/machine-unlearning-on-medqa-qf-100.md>): Machine Unlearning; MedQA QF=100; Forget Accuracy: 91.33.

- [Machine Unlearning on MHQA](<https://www.sota2.com/research/sota/machine-unlearning-on-mhqa.md>): Machine Unlearning; MHQA; Anxiety FR: 76.5.

- [Machine Unlearning on MedMCQA](<https://www.sota2.com/research/sota/machine-unlearning-on-medmcqa.md>): Machine Unlearning; MedMCQA; Forgetting Rate: 78.9.

- [Privacy Protection Analysis on MedMCQA (test)](<https://www.sota2.com/research/sota/privacy-protection-analysis-on-medmcqa-test.md>): Privacy Protection Analysis; MedMCQA (test); MIA Score: 0.82.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.02443>)

[PDF](<https://arxiv.org/pdf/2503.02443.pdf>)