paper-with-me

Papers

BBTv2: Towards a Gradient-Free Future with Large Language Models

2022-05-23 · Tianxiang Sun, Zhengfu He, Hong Qian, Yunhua Zhou, Xuanjing Huang, Xipeng Qiu

Most downstream adaptation methods tune all or part of the parameters of pre-trained models (PTMs) through gradient descent, where the tuning cost increases linearly with the growth of the model size. By contrast, gradient-free methods only require the forward computation of the PTM to tune the prompt, retaining the benefits of efficient tuning and deployment. Though, past work on gradient-free tuning often introduces gradient descent to seek a good initialization of prompt and lacks versatility across tasks and PTMs. In this paper, we present BBTv2, an improved version of Black-Box Tuning, to drive PTMs for few-shot learning. We prepend continuous prompts to every layer of the PTM and propose a divide-and-conquer gradient-free algorithm to optimize the prompts at different layers alternately. Extensive experiments across various tasks and PTMs show that BBTv2 can achieve comparable performance to full model tuning and state-of-the-art parameter-efficient methods (e.g., Adapter, LoRA, BitFit, etc.) under few-shot settings while maintaining much fewer tunable parameters.

📄 PDF Abstract BibTeX arXiv:2205.11200

Code (1)

txsun1997/black-box-tuning 공식 구현 pytorch

Tasks

Few-Shot LearningLanguage Modelling

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

Technical Report -- Competition Solution for Prompt Tuning using Pretrained Language Model

2022-12-13 · Jiang-Long Song, Wu-He Zou, Feng Li, Xiao-Lei Qin 외

Prompt tuning recently becomes a hot-spot in the applications of large pretrained language models on specific downstream tasks. Regarding the Language Model as a Service (LMaaS), black-box tuning using derivative-free op…

Few-Shot LearningLanguage ModelingLanguage Modelling

Gradient Sparsification For \emph{Masked Fine-Tuning} of Transformers

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Fine-tuning masked language models is widely adopted for transfer learning to downstream tasks and can be achieved by (1) freezing gradients of the pretrained network or only updating gradients of a newly added classific…

Transfer LearningXLM-R

Gradient Sparsification For Masked Fine-Tuning of Transformers

2023-07-19 · James O' Neill, Sourav Dutta

Fine-tuning pretrained self-supervised language models is widely adopted for transfer learning to downstream tasks. Fine-tuning can be achieved by freezing gradients of the pretrained network and only updating gradients …

Transfer Learning

Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization

2026-01-15 · Jiarui Yao, Ruida Wang, Hao Bai, Tong Zhang arxiv

Group Relative Policy Optimization (GRPO) is widely used for critic-free Large Language Model (LLM) post-training, but its KL regularization is usually implemented as a local loss-side token penalty. We show that this mi…

Reinforcement LearningMathematical Reasoning

When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario

2023-05-17 · Chengcheng Han, Liqing Cui, Renyu Zhu, Jianing Wang 외

Large pre-trained language models (PLMs) have garnered significant attention for their versatility and potential for solving a wide spectrum of natural language processing (NLP) tasks. However, the cost of running these …

Knowledge Distillation