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

• URL: http://arxiv.org/abs/2503.02443v1
• Date: Tue, 04 Mar 2025 09:39:09 GMT
• Title: AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking
• Authors: Iraklis Premptis, Maria Lymperaiou, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Athanasios Voulodimos, Giorgos Stamou,
• Abstract summary: We leverage parameter-efficient, gradient-based unlearning using low-rank adaptation and layer-focused fine-tuning.<n>We employ data chunking, splitting forget data into disjoint partitions and merging them with cyclically sampled retain samples at a pre-defined ratio.
• Score: 5.535042121804845
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data [54.934578742209716]
  In real-world NLP applications, Large Language Models (LLMs) offer promising solutions due to their extensive training on vast datasets.<n>LLKD is an adaptive sample selection method that incorporates signals from both the teacher and student.<n>Our comprehensive experiments show that LLKD achieves superior performance across various datasets with higher data efficiency.
  arXiv  Detail & Related papers  (2024-11-12T18:57:59Z)
• Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review [50.78587571704713]
  Learn-Focus-Review (LFR) is a dynamic training approach that adapts to the model's learning progress.<n>LFR tracks the model's learning performance across data blocks (sequences of tokens) and prioritizes revisiting challenging regions of the dataset.<n>Compared to baseline models trained on the full datasets, LFR consistently achieved lower perplexity and higher accuracy.
  arXiv  Detail & Related papers  (2024-09-10T00:59:18Z)
• RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models [23.91608718129775]
  We propose RKLD, a novel textbfReverse textbfKL-Divergence-based Knowledge textbfDistillation unlearning algorithm for large language models (LLMs) We achieve significant forget quality and effectively maintain the model utility in our experiments.
  arXiv  Detail & Related papers  (2024-06-04T05:51:43Z)
• Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding [9.112203072394648]
  Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples.
  arXiv  Detail & Related papers  (2023-12-08T19:26:13Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• Beyond Transfer Learning: Co-finetuning for Action Localisation [64.07196901012153]
  We propose co-finetuning -- simultaneously training a single model on multiple upstream'' and downstream'' tasks. We demonstrate that co-finetuning outperforms traditional transfer learning when using the same total amount of data. We also show how we can easily extend our approach to multiple upstream'' datasets to further improve performance.
  arXiv  Detail & Related papers  (2022-07-08T10:25:47Z)
• ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification [21.933876113300897]
  We adopt an alternative approach by transfer learning on an ensemble of related tasks using prototypical networks under the meta-learning paradigm. Using intent classification as a case study, we demonstrate that increasing variability in training tasks can significantly improve classification performance.
  arXiv  Detail & Related papers  (2021-01-28T00:19:13Z)
• DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks [88.62288327934499]
  We propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2020-11-03T07:49:15Z)
• Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning [23.00300794016583]
  State-of-the-art natural language understanding classification models follow two-stages. We propose a supervised contrastive learning (SCL) objective for the fine-tuning stage. Our proposed fine-tuning objective leads to models that are more robust to different levels of noise in the fine-tuning training data.
  arXiv  Detail & Related papers  (2020-11-03T01:10:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.