paper-with-me

Papers

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

2022-11-03 · Haojie Zhang, Ge Li, Jia Li, Zhongjin Zhang, Yuqi Zhu, Zhi Jin

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by overfitting and representation degradation. In this paper, we propose a Dynamic Parameter Selection (DPS) algorithm for the large-scale pre-trained models during fine-tuning, which adaptively selects a more promising subnetwork to perform staging updates based on gradients of back-propagation. Experiments on the GLUE benchmark show that DPS outperforms previous fine-tuning methods in terms of overall performance and stability, and consistently achieves better results with variable pre-trained language models. In addition, DPS brings a large magnitude of improvement in out-of-domain transferring experiments and low-resource scenarios, which shows that it can maintain stable general contextual features and reduce the representation collapse. We release our code at https://github.com/ZhangHaojie077/DPS

📄 PDF Abstract BibTeX arXiv:2211.01642

Code (1)

zhanghaojie077/dps 공식 구현 jax

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

2025-02-27 · Moo Jin Kim, Chelsea Finn, Percy Liang

Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. …

Action GenerationChunkingImitation LearningVision-Language-Action

Optimizing Multi-Modality Trackers via Significance-Regularized Tuning

2025-08-24 · Zhiwen Chen, Jinjian Wu, Zhiyu Zhu, Yifan Zhang 외 arxiv

This paper tackles the critical challenge of optimizing multi-modality trackers by effectively adapting pre-trained models for RGB data. Existing fine-tuning paradigms oscillate between excessive flexibility and over-res…

Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence

2026-02-28 · Quoc Minh Nguyen, Trung Le, Jing Wu, Anh Tuan Bui 외 arxiv

Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as harmful fine-tuning attacks. In this wor…

Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps

2026-04-06 · Jianwei Zhang, Sihan Cao, Chaoning Zhang, Ziming Hong 외 arxiv

Recent large-scale generative models enable high-quality 3D synthesis. However, the public accessibility of pre-trained weights introduces a critical vulnerability. Adversaries can fine-tune these models to steal special…

Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs

2024-10-14 · Ishan Jindal, Chandana Badrinath, Pranjal Bharti, Lakkidi Vinay 외

Large Language Models (LLMs) for public use require continuous pre-training to remain up-to-date with the latest data. The models also need to be fine-tuned with specific instructions to maintain their ability to follow …

Instruction Following