PromptAL: Sample-Aware Dynamic Soft Prompts for Few-Shot Active Learning

TL;DR

PromptAL introduces a novel sample-aware dynamic soft prompt method that leverages unlabeled data to better align the empirical distribution with the target, enhancing active learning in few-shot scenarios.

Contribution

It proposes a hybrid active learning framework that uses unlabeled data to construct dynamic soft prompts, improving decision boundary accuracy and sample selection.

Findings

Outperforms nine baseline methods on multiple datasets.

Effectively aligns empirical and target distributions in few-shot active learning.

Enhances sample diversity and uncertainty estimation for better data selection.

Abstract

Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision boundary and perform uncertainty or diversity estimation, subsequently identifying potential high-quality samples. In few-shot scenarios, the empirical distribution often diverges significantly from the target distribution, causing the decision boundary to shift away from its optimal position. However, existing methods overlook the role of unlabeled samples in enhancing the empirical distribution to better align with the target distribution, resulting in a suboptimal decision boundary and the selection of samples that inadequately represent the target distribution. To address this, we propose a hybrid AL framework, termed \textbf{PromptAL} (Sample-Aware Dynamic Soft \textbf{Prompts} for Few-Shot \textbf{A}ctive \textbf{L}earning). This framework accounts for the contribution of each unlabeled data point in aligning the current empirical distribution with the target distribution, thereby optimizing the decision boundary. Specifically, PromptAL first leverages unlabeled data to construct sample-aware dynamic soft prompts that adjust the model's predictive distribution and decision boundary. Subsequently, based on the adjusted decision boundary, it integrates uncertainty estimation with both global and local diversity to select high-quality samples that more accurately represent the target distribution. Experimental results on six in-domain and three out-of-domain datasets show that PromptAL achieves superior performance over nine baselines. Our codebase is openly accessible.