paper-with-me

Papers

Quantization-Robust LLM Unlearning via Low-Rank Adaptation

2026-02-13 · João Vitor Boer Abitante, Joana Meneguzzo Pasquali, Luan Fonseca Garcia, Ewerton de Oliveira, Thomas da Silva Paula, Rodrigo C. Barros, Lucas S. Kupssinskü arxiv

Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask unlearning updates, causing quantized models to revert to pre-unlearning behavior. We show that standard full-parameter fine-tuning often induces parameter changes that are too small to survive 4-bit quantization. We propose quantization-robust unlearning via low-rank adaptation (LoRA): we freeze the base model and concentrate unlearning into trainable adapters so that the effective update is preserved after quantization. On Llama-2-7B evaluated with MUSE dataset (BOOKS and NEWS), LoRA improves 4-bit utility by up to 7.93 points (NPO+GDR on BOOKS: 50.17 to 58.10) and yields higher 4-bit utility on NEWS for GA+GDR (40.06 to 44.82, increase of 4.76). LoRA also substantially reduces privacy leakage under 4-bit PTQ, e.g., for GA+KLR on BOOKS, PrivLeak moves from -25.68 to -5.86 (closer to ideal 0), while maintaining strong forgetting (VerMem and KnowMem near 0). Thus, using LoRA for Machine Unlearning is beneficial for scenarios where quantization is necessary for model deployment.

📄 PDF Abstract BibTeX arXiv:2602.13151

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs

2026-01-21 · Himanshu Mishra, Kanwal Mehreen arxiv

Machine unlearning aims to remove specific knowledge (e.g., copyrighted or private data) from a trained model without full retraining. In practice, models are often quantized (e.g., 4-bit) for deployment, but we find tha…

Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization

2025-03-17 · Jan Bronec, Jindřich Helcl

We present a submission to the SemEval 2025 shared task on unlearning sensitive content from LLMs. Our approach employs negative preference optimization using low-rank adaptation. We show that we can utilize this combina…

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

2025-03-04 · Iraklis Premptis, Maria Lymperaiou, Giorgos Filandrianos, Orfeas Menis Mastromichalakis 외

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, gra…

ChunkingGeneral Knowledge

Catastrophic Failure of LLM Unlearning via Quantization

2024-10-21 · Zhiwei Zhang, Fali Wang, Xiaomin Li, Zongyu Wu 외

Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensit…

Machine UnlearningQuantization

Erase to Retain: Low Rank Adaptation Guided Selective Unlearning in Medical Segmentation Networks

2025-11-20 · Nirjhor Datta, Md. Golam Rabiul Alam arxiv

The ability to selectively remove knowledge from medical segmentation networks is increasingly important for privacy compliance, ethical deployment, and continual dataset revision. We introduce Erase to Retain, a control…

Medical Image Segmentation