paper-with-me

Papers

Parameter-Efficient Tuning by Manipulating Hidden States of Pretrained Language Models For Classification Tasks

2022-04-10 · Haoran Yang, Piji Li, Wai Lam

Parameter-efficient tuning aims to distill knowledge for downstream tasks by optimizing a few introduced parameters while freezing the pretrained language models (PLMs). Continuous prompt tuning which prepends a few trainable vectors to the embeddings of input is one of these methods and has drawn much attention due to its effectiveness and efficiency. This family of methods can be illustrated as exerting nonlinear transformations of hidden states inside PLMs. However, a natural question is ignored: can the hidden states be directly used for classification without changing them? In this paper, we aim to answer this question by proposing a simple tuning method which only introduces three trainable vectors. Firstly, we integrate all layers hidden states using the introduced vectors. And then, we input the integrated hidden state(s) to a task-specific linear classifier to predict categories. This scheme is similar to the way ELMo utilises hidden states except that they feed the hidden states to LSTM-based models. Although our proposed tuning scheme is simple, it achieves comparable performance with prompt tuning methods like P-tuning and P-tuning v2, verifying that original hidden states do contain useful information for classification tasks. Moreover, our method has an advantage over prompt tuning in terms of time and the number of parameters.

📄 PDF Abstract BibTeX arXiv:2204.04596

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
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 $x$…
ELMo Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and…

Similar Papers 제목 키워드 기반

Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning

2022-10-18 · Shuo Xie, Jiahao Qiu, Ankita Pasad, Li Du 외

While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We investigate whether one could make a task-s…

Language ModelingLanguage ModellingTransfer Learning

Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters

2022-10-18 · Hongyu Zhao, Hao Tan, Hongyuan Mei

Adapter-tuning is a paradigm that transfers a pretrained language model to downstream tasks by adding and tuning a small number of new parameters. Previously proposed adapter architectures are all feed-forward neural net…

Language ModelingLanguage ModellingMixture-of-ExpertsTransfer Learning

Prefix Propagation: Parameter-Efficient Tuning for Long Sequences

2023-05-20 · Jonathan Li, Will Aitken, Rohan Bhambhoria, Xiaodan Zhu

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequence…

Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models

2025-06-10 · Sungwon Hwang, Hyojin Jang, Kinam Kim, Minho Park 외

Fine-tuning Video Diffusion Models (VDMs) at the user level to generate videos that reflect specific attributes of training data presents notable challenges, yet remains underexplored despite its practical importance. Me…

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

2026-04-21 · Xianming Li, Zongxi Li, Tsz-fung Andrew Lee, Jing Li 외 arxiv

Parameter-efficient fine-tuning (PEFT) reduces the training cost of full-parameter fine-tuning for large language models (LLMs) by training only a small set of task-specific parameters while freezing the pretrained backb…

parameter-efficient fine-tuning