中文
相关论文

相关论文: AcTune: Uncertainty-aware Active Self-Training for…

200 篇论文

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

计算与语言 · 计算机科学 2023-02-17 Tong Guo

Process Reward Models (PRMs) provide step-level supervision to large language models (LLMs), but scaling up training data annotation remains challenging for both humans and LLMs. To address this limitation, we propose an active learning…

机器学习 · 计算机科学 2025-04-16 Keyu Duan , Zichen Liu , Xin Mao , Tianyu Pang , Changyu Chen , Qiguang Chen , Michael Qizhe Shieh , Longxu Dou

Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…

计算与语言 · 计算机科学 2020-06-30 Subhabrata Mukherjee , Ahmed Hassan Awadallah

As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook…

计算与语言 · 计算机科学 2024-06-10 Yikun Wang , Rui Zheng , Liang Ding , Qi Zhang , Dahua Lin , Dacheng Tao

Active learning (AL) optimizes data labeling efficiency by selecting the most informative instances for annotation. A key component in this procedure is an acquisition function that guides the selection process and identifies the suitable…

机器学习 · 计算机科学 2024-10-08 Abdul Hameed Azeemi , Ihsan Ayyub Qazi , Agha Ali Raza

Many active learning methods belong to the retraining-based approaches, which select one unlabeled instance, add it to the training set with its possible labels, retrain the classification model, and evaluate the criteria that we base our…

机器学习 · 统计学 2017-03-01 Yazhou Yang , Marco Loog

The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the…

机器学习 · 计算机科学 2023-10-23 Jianing Wang , Qiushi Sun , Nuo Chen , Chengyu Wang , Jun Huang , Ming Gao , Xiang Li

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

计算与语言 · 计算机科学 2024-10-07 Christopher Schröder , Gerhard Heyer

Fine-tuning Large Language Models (LLMs) is now a common approach for text classification in a wide range of applications. When labeled documents are scarce, active learning helps save annotation efforts but requires retraining of massive…

机器学习 · 计算机科学 2024-02-27 Artem Vysogorets , Achintya Gopal

Recent Vision-based Large Language Models~(VisionLLMs) for autonomous driving have seen rapid advancements. However, such promotion is extremely dependent on large-scale high-quality annotated data, which is costly and labor-intensive. To…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Chaoqun Wang , Jie Yang , Xiaobin Hong , Ruimao Zhang

In recent years, deep neural networks (DNNs) have been found very successful for multi-label classification (MLC) of remote sensing (RS) images. Self-supervised pre-training combined with fine-tuning on a randomly selected small training…

计算机视觉与模式识别 · 计算机科学 2023-06-22 Lars Möllenbrok , Begüm Demir

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are…

计算与语言 · 计算机科学 2023-11-03 Song Wang , Zhen Tan , Ruocheng Guo , Jundong Li

Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…

计算机视觉与模式识别 · 计算机科学 2024-03-14 Dror Simon , Miriam Farber , Roman Goldenberg

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…

机器学习 · 计算机科学 2024-06-18 Jiahan Zhang , Qi Wei , Feng Liu , Lei Feng

Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…

计算与语言 · 计算机科学 2025-10-06 Neeraj Agrawal , Sriram Ganapathy

Neural sequence labeling (NSL) aims at assigning labels for input language tokens, which covers a broad range of applications, such as named entity recognition (NER) and slot filling, etc. However, the satisfying results achieved by…

计算与语言 · 计算机科学 2023-02-20 Jianing Wang , Chengyu Wang , Jun Huang , Ming Gao , Aoying Zhou

Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…

计算与语言 · 计算机科学 2023-10-09 Zhengxiang Shi , Aldo Lipani

Active learning strives to reduce annotation costs by choosing the most critical examples to label. Typically, the active learning strategy is contingent on the classification model. For instance, uncertainty sampling depends on poorly…

计算与语言 · 计算机科学 2020-10-26 Michelle Yuan , Hsuan-Tien Lin , Jordan Boyd-Graber

The pretraining-finetuning paradigm has gained popularity in various computer vision tasks. In this paradigm, the emergence of active finetuning arises due to the abundance of large-scale data and costly annotation requirements. Active…

计算机视觉与模式识别 · 计算机科学 2024-02-28 Wenshuai Xu , Zhenghui Hu , Yu Lu , Jinzhou Meng , Qingjie Liu , Yunhong Wang

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…

计算与语言 · 计算机科学 2023-05-30 Jiaxin Ge , Hongyin Luo , Yoon Kim , James Glass
‹ 上一页 1 2 3 10 下一页 ›