paper-with-me

홈 › Papers

SPAFIT: Stratified Progressive Adaptation Fine-tuning for Pre-trained Large Language Models

2024-04-30 · Samir Arora, Liangliang Wang

Full fine-tuning is a popular approach to adapt Transformer-based pre-trained large language models to a specific downstream task. However, the substantial requirements for computational power and storage have discouraged its widespread use. Moreover, increasing evidence of catastrophic forgetting and overparameterization in the Transformer architecture has motivated researchers to seek more efficient fine-tuning (PEFT) methods. Commonly known parameter-efficient fine-tuning methods like LoRA and BitFit are typically applied across all layers of the model. We propose a PEFT method, called Stratified Progressive Adaptation Fine-tuning (SPAFIT), based on the localization of different types of linguistic knowledge to specific layers of the model. Our experiments, conducted on nine tasks from the GLUE benchmark, show that our proposed SPAFIT method outperforms other PEFT methods while fine-tuning only a fraction of the parameters adjusted by other methods.

📄 PDF Abstract BibTeX arXiv:2405.00201

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition

2024-10-13 · Kha Nhat Le, Hoang-Tuan Nguyen, Hung Tien Tran, Thanh Duc Ngo

Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR), especially where training and testing data reside in different domains. The efficacy of existing UDA approaches tend…

Domain AdaptationOptical Character Recognition (OCR)Pseudo LabelScene Text Recognition+3

Stratified Consistency Distillation for Natural Language Formalization

2026-08-31 · Zhichao Hou, Ferhat Erata, Joe Lilien, MohamadAli Torkamani arxiv

Neurosymbolic reasoning has shown promising success in addressing complex reasoning tasks by combining large language models (LLMs) and symbolic solvers. While this approach shows promise, a fundamental challenge remains…

Prompt Engineering

Progtuning: Progressive Fine-tuning Framework for Transformer-based Language Models

2025-06-26 · Xiaoshuang Ji, Zhendong Zhao, Xiaojun Chen, Xin Zhao 외

Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient f…

parameter-efficient fine-tuning

PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation

2024-06-13 · Injoon Hwang, Haewon Park, Youngwan Lee, Jooyoung Yang 외

Low-rank adaption (LoRA) is a prominent method that adds a small number of learnable parameters to the frozen pre-trained weights for parameter-efficient fine-tuning. Prompted by the question, ``Can we make its represent…

Knowledge DistillationModel Compressionparameter-efficient fine-tuning

PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation

2025-03-03 · Linhai Zhang, Jialong Wu, Deyu Zhou, Yulan He

Personalized large language models (LLMs) aim to tailor their outputs to user preferences. Recent advances in parameter-efficient fine-tuning (PEFT) methods have highlighted the effectiveness of adapting population-level…

Mixture-of-Expertsparameter-efficient fine-tuning