English
Related papers

Related papers: Mixout: Effective Regularization to Finetune Large…

200 papers

Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical…

Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially improve both the robustness and the generalization of the…

Machine Learning · Computer Science 2021-03-19 Linjun Zhang , Zhun Deng , Kenji Kawaguchi , Amirata Ghorbani , James Zou

Dropout and other feature noising schemes control overfitting by artificially corrupting the training data. For generalized linear models, dropout performs a form of adaptive regularization. Using this viewpoint, we show that the dropout…

Machine Learning · Statistics 2013-11-04 Stefan Wager , Sida Wang , Percy Liang

Pretrained language models have been shown to exhibit biases and social stereotypes. Prior work on debiasing these models has largely focused on modifying embedding spaces during pretraining, which is not scalable for large models.…

Artificial Intelligence · Computer Science 2026-02-03 Deep Gandhi , Katyani Singh , Nidhi Hegde

In the last decade, exponential data growth supplied the machine learning-based algorithms' capacity and enabled their usage in daily life activities. Additionally, such an improvement is partially explained due to the advent of deep…

Machine Learning · Computer Science 2022-03-08 Claudio Filipi Goncalves do Santos , Mateus Roder , Leandro A. Passos , João P. Papa

Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of…

Computation and Language · Computer Science 2023-10-02 Ping Yu , Tianlu Wang , Olga Golovneva , Badr AlKhamissi , Siddharth Verma , Zhijing Jin , Gargi Ghosh , Mona Diab , Asli Celikyilmaz

In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response…

Computation and Language · Computer Science 2021-01-19 Tianxing He , Jun Liu , Kyunghyun Cho , Myle Ott , Bing Liu , James Glass , Fuchun Peng

Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels. This technique is known to improve the generalization…

Machine Learning · Computer Science 2023-10-17 Yingtian Zou , Vikas Verma , Sarthak Mittal , Wai Hoh Tang , Hieu Pham , Juho Kannala , Yoshua Bengio , Arno Solin , Kenji Kawaguchi

In recent years, neural machine translation (NMT) has become the dominant approach in automated translation. However, like many other deep learning approaches, NMT suffers from overfitting when the amount of training data is limited. This…

Computation and Language · Computer Science 2019-10-01 Inigo Jauregi Unanue , Ehsan Zare Borzeshi , Massimo Piccardi

The development of large language models leads to the formation of a pre-train-then-align paradigm, in which the model is typically pre-trained on a large text corpus and undergoes a tuning stage to align the model with human preference or…

Computation and Language · Computer Science 2025-03-19 Kaiser Sun , Mark Dredze

State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…

Computation and Language · Computer Science 2020-04-30 Evani Radiya-Dixit , Xin Wang

Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fine-tuning is often employed and has emerged as the de facto…

Machine Learning · Computer Science 2025-03-14 Shilong Wang , Jianchun Liu , Hongli Xu , Jiaming Yan , Xianjun Gao

We propose BlackOut, an approximation algorithm to efficiently train massive recurrent neural network language models (RNNLMs) with million word vocabularies. BlackOut is motivated by using a discriminative loss, and we describe a new…

Machine Learning · Computer Science 2016-04-01 Shihao Ji , S. V. N. Vishwanathan , Nadathur Satish , Michael J. Anderson , Pradeep Dubey

With the surge of ChatGPT,the use of large models has significantly increased,rapidly rising to prominence across the industry and sweeping across the internet. This article is a comprehensive review of fine-tuning methods for large models.…

Machine Learning · Computer Science 2024-04-16 Benjue Weng

Fine-tuning large-scale pre-trained language models has been demonstrated effective for various natural language processing (NLP) tasks. Previous studies have established that incorporating adversarial training during the fine-tuning stage…

Computation and Language · Computer Science 2023-06-29 Zhehua Zhong , Tianyi Chen , Zhen Wang

A widely used algorithm for transfer learning is fine-tuning, where a pre-trained model is fine-tuned on a target task with a small amount of labeled data. When the capacity of the pre-trained model is significantly larger than the size of…

Machine Learning · Computer Science 2025-08-15 Dongyue Li , Hongyang R. Zhang

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Computation and Language · Computer Science 2021-07-13 Hang Hua , Xingjian Li , Dejing Dou , Cheng-Zhong Xu , Jiebo Luo

As language models scale, the amount of data they require grows -- yet many target data sources, such as low-resource languages or specialized domains, are inherently limited in size. A common strategy is to mix this scarce but valuable…

Machine Learning · Computer Science 2026-05-18 Anastasiia Sedova , Skyler Seto , Natalie Schluter , Pierre Ablin

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Ghada Sokar , Gintare Karolina Dziugaite , Anurag Arnab , Ahmet Iscen , Pablo Samuel Castro , Cordelia Schmid

Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Jonas Ngnawe , Marianne Abemgnigni Njifon , Jonathan Heek , Yann Dauphin
‹ Prev 1 4 5 6 7 8 10 Next ›