English
Related papers

Related papers: Pruning Unsafe Tickets: A Resource-Efficient Frame…

200 papers

With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the safety of this fine-tuning process more important than ever.…

Cryptography and Security · Computer Science 2025-07-28 Hao Li , Lijun Li , Zhenghao Lu , Xianyi Wei , Rui Li , Jing Shao , Lei Sha

This study introduces an innovative approach aimed at the efficient pruning of neural networks, with a particular focus on their deployment on edge devices. Our method involves the integration of the Lottery Ticket Hypothesis (LTH) with the…

Information Retrieval · Computer Science 2024-01-22 Rajaram R , Manoj Bharadhwaj , Vasan VS , Nargis Pervin

Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs). However, this approach is typically more expensive than traditional fine-tuning because of the necessity to generate…

Computation and Language · Computer Science 2022-12-01 Zhiheng Xi , Rui Zheng , Tao Gui , Qi Zhang , Xuanjing Huang

Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the performance of inference. Several recent results have explored the possibility of pruning at initialization time…

Machine Learning · Computer Science 2020-09-29 Jonathan Frankle , Gintare Karolina Dziugaite , Daniel M. Roy , Michael Carbin

Yes. In this paper, we investigate strong lottery tickets in generative models, the subnetworks that achieve good generative performance without any weight update. Neural network pruning is considered the main cornerstone of model…

Computer Vision and Pattern Recognition · Computer Science 2022-12-19 Sangyeop Yeo , Yoojin Jang , Jy-yong Sohn , Dongyoon Han , Jaejun Yoo

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models. However, these…

Computation and Language · Computer Science 2022-11-15 Rui Zheng , Rong Bao , Yuhao Zhou , Di Liang , Sirui Wang , Wei Wu , Tao Gui , Qi Zhang , Xuanjing Huang

Non-uniform structured network pruning methods can effectively reduce Large Language Model (LLM) size by eliminating redundant channels or layers, offering lower performance degradation than uniform strategies. However, existing non-uniform…

Machine Learning · Computer Science 2025-08-07 Zuxin Ma , Yunhe Cui , Yongbin Qin

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…

Computation and Language · Computer Science 2023-10-06 Xiangyu Qi , Yi Zeng , Tinghao Xie , Pin-Yu Chen , Ruoxi Jia , Prateek Mittal , Peter Henderson

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to…

Machine Learning · Computer Science 2025-06-25 Shuang Ao , Yi Dong , Jinwei Hu , Sarvapali Ramchurn

Federated learning (FL) is a collaborative learning paradigm for decentralized private data from mobile terminals (MTs). However, it suffers from issues in terms of communication, resource of MTs, and privacy. Existing privacy-preserving FL…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-03 Yifan Shi , Kang Wei , Li Shen , Jun Li , Xueqian Wang , Bo Yuan , Song Guo

In this paper, we explore the performance of different pruning methods in the context of the lottery ticket hypothesis. We compare the performance of L1 unstructured pruning, Fisher pruning, and random pruning on different network…

Machine Learning · Computer Science 2023-03-29 Eirik Fladmark , Muhammad Hamza Sajjad , Laura Brinkholm Justesen

As large reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses,…

Computation and Language · Computer Science 2026-03-31 Raj Vardhan Tomar , Preslav Nakov , Yuxia Wang

Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on this framework and propose a new pruning at initialization…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Leonardo Iurada , Marco Ciccone , Tatiana Tommasi

The exponential growth in LLM scales, with parameters soaring from billions to trillions, has necessitated distributed pretraining across large clusters comprising thousands to tens of thousands of devices. While hybrid parallelization…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-21 Lu Zhao , Rong Shi , Shaoqing Zhang , Shangchao Su , Ziqing Yin , Zhiyan Cui , Hongfeng Sun , Baoguo He , Yueqiang Chen , Liang Dong , Xiyuan Li , Lingbin Wang , Lijun Ma , Qiang Huang , Ting Liu , Chong Wang , Can Wei

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

Cryptography and Security · Computer Science 2026-04-10 Rui Zhang , Hongwei Li , Yun Shen , Xinyue Shen , Wenbo Jiang , Guowen Xu , Yang Liu , Michael Backes , Yang Zhang

Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…

Machine Learning · Computer Science 2025-08-19 Minseon Kim , Jin Myung Kwak , Lama Alssum , Bernard Ghanem , Philip Torr , David Krueger , Fazl Barez , Adel Bibi

With the emergence of the Software 3.0 era, there is a growing trend of compressing and integrating large models into software systems, with significant societal implications. Regrettably, in numerous instances, model compression techniques…

Software Engineering · Computer Science 2024-07-04 Xuanqi Gao , Weipeng Jiang , Juan Zhai , Shiqing Ma , Xiaoyu Zhang , Chao Shen

Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the original model with commensurate training steps. While this…

Machine Learning · Computer Science 2020-03-13 Bai Li , Shiqi Wang , Yunhan Jia , Yantao Lu , Zhenyu Zhong , Lawrence Carin , Suman Jana

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Computation and Language · Computer Science 2023-10-03 Tianci Xue , Ziqi Wang , Heng Ji

Recognition tasks, such as object recognition and keypoint estimation, have seen widespread adoption in recent years. Most state-of-the-art methods for these tasks use deep networks that are computationally expensive and have huge memory…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Sharath Girish , Shishira R. Maiya , Kamal Gupta , Hao Chen , Larry Davis , Abhinav Shrivastava