paper-with-me

Papers

ALLSH: Active Learning Guided by Local Sensitivity and Hardness

2022-05-10 · Findings (NAACL) 2022 7 · Shujian Zhang, Chengyue Gong, Xingchao Liu, Pengcheng He, Weizhu Chen, Mingyuan Zhou

Active learning, which effectively collects informative unlabeled data for annotation, reduces the demand for labeled data. In this work, we propose to retrieve unlabeled samples with a local sensitivity and hardness-aware acquisition function. The proposed method generates data copies through local perturbations and selects data points whose predictive likelihoods diverge the most from their copies. We further empower our acquisition function by injecting the select-worst case perturbation. Our method achieves consistent gains over the commonly used active learning strategies in various classification tasks. Furthermore, we observe consistent improvements over the baselines on the study of prompt selection in prompt-based few-shot learning. These experiments demonstrate that our acquisition guided by local sensitivity and hardness can be effective and beneficial for many NLP tasks.

📄 PDF Abstract BibTeX arXiv:2205.04980

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningFew-Shot LearningSensitivity

Similar Papers 제목 키워드 기반

AllShowers: One model for all calorimeter showers

2026-01-16 · Thorsten Buss, Henry Day-Hall, Frank Gaede, Gregor Kasieczka 외 arxiv

Accurate and efficient detector simulation is essential for modern collider experiments. To reduce the high computational cost, various fast machine learning surrogate models have been proposed. Traditional surrogate mod…

Sheaf-Laplacian Obstruction and Projection Hardness for Cross-Modal Compatibility on a Modality-Independent Site

2026-04-08 · Tibor Sloboda arxiv

Cross-modal representations vary in how easily they can be aligned, and compatibility is generally non-transitive: two modalities may align through an intermediate modality at lower complexity than through a direct map. …

Statistical guided-waves-based SHM via stochastic non-parametric time series models

2021-01-27 · Ahmad Amer, Fotis Kopsaftopoulos

Damage detection in active-sensing, guided-waves-based Structural Health Monitoring (SHM) has evolved through multiple eras of development during the past decades. Nevertheless, there still exists a number of challenges …

Decision MakingSensitivityStructural Health MonitoringTime Series+1

Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors

2025-05-19 · Junyi Chen, Alap Kshirsagar, Frederik Heller, Mario Gómez Andreu 외

One of the most important object properties that humans and robots perceive through touch is hardness. This paper investigates information-theoretic active sampling strategies for sample-efficient hardness classification…

Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios

2022-11-11 · Ngoc Dang Nguyen, Lan Du, Wray Buntine, Changyou Chen 외

Domain adaptation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as bioNER, domain adaptation methods often suffer from the challenging linguistic cha…

Domain Adaptation