paper-with-me

Papers

Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models

2021-06-24 · Findings (ACL) 2022 5 · Robert L. Logan IV, Ivana Balažević, Eric Wallace, Fabio Petroni, Sameer Singh, Sebastian Riedel

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably reduce the need for prompt engineering. In fact, one can use null prompts, prompts that contain neither task-specific templates nor training examples, and achieve competitive accuracy to manually-tuned prompts across a wide range of tasks. While finetuning LMs does introduce new parameters for each downstream task, we show that this memory overhead can be substantially reduced: finetuning only the bias terms can achieve comparable or better accuracy than standard finetuning while only updating 0.1% of the parameters. All in all, we recommend finetuning LMs for few-shot learning as it is more accurate, robust to different prompts, and can be made nearly as efficient as using frozen LMs.

📄 PDF Abstract BibTeX arXiv:2106.13353

Code (2)

ucinlp/null-prompts 공식 구현 pytorch
facebookresearch/perfect pytorch

Tasks

Few-Shot LearningPrompt Engineering

Similar Papers 제목 키워드 기반

STT: Soft Template Tuning for Few-Shot Learning

2022-01-16 · ACL ARR January 2022 1 · Anonymous

With the rapid expansion of large pre-trained language models, fine-tuning all the model parameters for downstream tasks is becoming computationally prohibitive. The recently developed prompt-based methods freeze the ent…

Few-Shot LearningLanguage ModelingLanguage ModellingMasked Language Modeling+2

Revisiting Automated Prompting: Are We Actually Doing Better?

2023-04-07 · Yulin Zhou, Yiren Zhao, Ilia Shumailov, Robert Mullins 외

Current literature demonstrates that Large Language Models (LLMs) are great few-shot learners, and prompting significantly increases their performance on a range of downstream tasks in a few-shot learning setting. An att…

Few-Shot Learning

Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning

2022-10-14 · Tianxiang Sun, Zhengfu He, Qin Zhu, Xipeng Qiu 외

Prompt tuning is a parameter-efficient approach to adapting pre-trained language models to downstream tasks. Although prompt tuning has been shown to match the performance of full model tuning when training data is suffi…

Few-Shot LearningMachine Reading ComprehensionReading Comprehension

STT: Soft Template Tuning for Few-Shot Adaptation

2022-07-18 · Ping Yu, Wei Wang, Chunyuan Li, Ruiyi Zhang 외

Prompt tuning has been an extremely effective tool to adapt a pre-trained model to downstream tasks. However, standard prompt-based methods mainly consider the case of sufficient data of downstream tasks. It is still unc…

Few-Shot LearningLanguage ModelingLanguage ModellingMasked Language Modeling+2

The Power of Scale for Parameter-Efficient Prompt Tuning

2021-04-18 · EMNLP 2021 11 · Brian Lester, Rami Al-Rfou, Noah Constant

In this work, we explore "prompt tuning", a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GP…

Few-Shot Learning