paper-with-me

Papers

Improving and Simplifying Pattern Exploiting Training

2021-03-22 · EMNLP 2021 11 · Derek Tam, Rakesh R Menon, Mohit Bansal, Shashank Srivastava, Colin Raffel

Recently, pre-trained language models (LMs) have achieved strong performance when fine-tuned on difficult benchmarks like SuperGLUE. However, performance can suffer when there are very few labeled examples available for fine-tuning. Pattern Exploiting Training (PET) is a recent approach that leverages patterns for few-shot learning. However, PET uses task-specific unlabeled data. In this paper, we focus on few-shot learning without any unlabeled data and introduce ADAPET, which modifies PET's objective to provide denser supervision during fine-tuning. As a result, ADAPET outperforms PET on SuperGLUE without any task-specific unlabeled data. Our code can be found at https://github.com/rrmenon10/ADAPET.

📄 PDF Abstract BibTeX arXiv:2103.11955

Code (2)

rrmenon10/ADAPET 공식 구현 pytorch
ethanjperez/true_few_shot pytorch

Tasks

Few-Shot Learning

Similar Papers 제목 키워드 기반

Simplifying Neural Networks During Training

2026-07-30 · Lorenzo Sciandra, Samuele Fonio, Roberto Esposito arxiv

Understanding and exploiting the training dynamics of overparameterized deep neural networks remains a central challenge in modern machine learning. Recent evidence on Neural Collapse (NC) shows that class representation…

Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards

2024-03-27 · Yasin Sonmez, Neelay Junnarkar, Murat Arcak

Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same …

Model-based Reinforcement Learningreinforcement-learningReinforcement Learning

Signature features with the visibility transformation

2020-04-08 · Yue Wu, Hao Ni, Terence J. Lyons, Robin L. Hudson

In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stream into signature features in a unified …

Position

Enhancing Tabular Reasoning with Pattern Exploiting Training

2022-10-21 · Abhilash Reddy Shankarampeta, Vivek Gupta, Shuo Zhang

Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent pred…

Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?

2024-09-08 · Neeladri Bhuiya, Viktor Schlegel, Stefan Winkler

State-of-the-art Large Language Models (LLMs) are accredited with an increasing number of different capabilities, ranging from reading comprehension, over advanced mathematical and reasoning skills to possessing scientif…

Language ModellingReading Comprehension