Active Few-Shot Fine-Tuning
We study the question: How can we select the right data for fine-tuning to a specific task? We call this data selection problem active fine-tuning and show that it is an instance of transductive active learning, a novel generalization of classical active learning. We propose ITL, short for information-based transductive learning, an approach which samples adaptively to maximize information gained about the specified task. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We apply ITL to the few-shot fine-tuning of large neural networks and show that fine-tuning with ITL learns the task with significantly fewer examples than the state-of-the-art.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningGeneralization BoundsTransductive LearningSimilar Papers 제목 키워드 기반
MEAL: Stable and Active Learning for Few-Shot Prompting
Few-shot classification has made great strides due to foundation models that, through priming and prompting, are highly effective few-shot learners. However, this approach has high variance both across different sets of …
Active LearningFew-Shot LearningRTEFactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization
We present FactPEGASUS, an abstractive summarization model that addresses the problem of factuality during pre-training and fine-tuning: (1) We augment the sentence selection strategy of PEGASUS's (Zhang et al., 2020) pr…
Abstractive Text SummarizationContrastive LearningSentenceBoundary Matters: A Bi-Level Active Finetuning Framework
The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To mitigate this, the concept of active finetun…
Active LearningDenoisingDiversityImproving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation
Models pretrained with self-supervised objectives on large text corpora achieve state-of-the-art performance on English text summarization tasks. However, these models are typically fine-tuned on hundreds of thousands of…
Abstractive Text SummarizationData AugmentationText SummarizationPSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we designed a novel soft prompts architecture coupled with a prompt pre-training plus fine-tuning paradigm t…
Abstractive Text SummarizationDecoderText Generation