English
Related papers

Related papers: METRO: Efficient Denoising Pretraining of Large Sc…

200 papers

In this paper, we propose a two-phase training approach where pre-trained large language models are continually pre-trained on parallel data and then supervised fine-tuned with a small amount of high-quality parallel data. To investigate…

Computation and Language · Computer Science 2024-07-04 Minato Kondo , Takehito Utsuro , Masaaki Nagata

While large pre-trained models have enabled impressive results on a variety of downstream tasks, the largest existing models still make errors, and even accurate predictions may become outdated over time. Because detecting all such failures…

Machine Learning · Computer Science 2022-06-15 Eric Mitchell , Charles Lin , Antoine Bosselut , Chelsea Finn , Christopher D. Manning

Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However,…

Computation and Language · Computer Science 2022-05-05 Xuefeng Bai , Yulong Chen , Yue Zhang

The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological systems demonstrate highly sample-efficient…

Computation and Language · Computer Science 2026-05-21 Guan Wang , Changling Liu , Chenyu Wang , Cai Zhou , Yuhao Sun , Yifei Wu , Shuai Zhen , Luca Scimeca , Yasin Abbasi Yadkori

ELECTRA, the generator-discriminator pre-training framework, has achieved impressive semantic construction capability among various downstream tasks. Despite the convincing performance, ELECTRA still faces the challenges of monotonous…

Computation and Language · Computer Science 2023-05-09 Beiduo Chen , Shaohan Huang , Zihan Zhang , Wu Guo , Zhenhua Ling , Haizhen Huang , Furu Wei , Weiwei Deng , Qi Zhang

The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, RoBERTa, and GPT-2 require a huge compute budget to create a…

Computation and Language · Computer Science 2021-04-21 Luca Di Liello , Matteo Gabburo , Alessandro Moschitti

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…

Computation and Language · Computer Science 2021-09-06 Yingmei Guo , Linjun Shou , Jian Pei , Ming Gong , Mingxing Xu , Zhiyong Wu , Daxin Jiang

Curriculum learning-organizing training data from easy to hard-has improved efficiency across machine learning domains, yet remains underexplored for language model pretraining. We present the first systematic investigation of curriculum…

Computation and Language · Computer Science 2026-01-29 Yang Zhang , Amr Mohamed , Hadi Abdine , Guokan Shang , Michalis Vazirgiannis

Large language models (LLMs), especially generative pre-trained transformers (GPTs), have recently demonstrated outstanding ability in information comprehension and problem-solving. This has motivated many studies in applying LLMs to…

Machine Learning · Computer Science 2024-05-21 Han Zhang , Akram Bin Sediq , Ali Afana , Melike Erol-Kantarci

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models…

Computation and Language · Computer Science 2024-04-19 Jiabao Ji , Bairu Hou , Zhen Zhang , Guanhua Zhang , Wenqi Fan , Qing Li , Yang Zhang , Gaowen Liu , Sijia Liu , Shiyu Chang

Modeling large-scale time series has gained significant attention in recent years. However, its direct application in finance remains challenging due to substantial differences in data characteristics across domains. Specifically, financial…

Artificial Intelligence · Computer Science 2025-10-22 Yuanjian Xu , Anxian Liu , Jianing Hao , Zhenzhuo Li , Shichang Meng , Guang Zhang

By increasing model parameters but activating them sparsely when performing a task, the use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large Language Models (LLMs) without increasing the inference…

Computation and Language · Computer Science 2025-06-10 Zeliang Zhang , Xiaodong Liu , Hao Cheng , Chenliang Xu , Jianfeng Gao

Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…

Computation and Language · Computer Science 2015-03-19 Sébastien Jean , Kyunghyun Cho , Roland Memisevic , Yoshua Bengio

Pre-training on public data is an effective method to improve the performance for federated learning (FL) with differential privacy (DP). This paper investigates how large language models (LLMs) trained on public data can improve the…

Machine Learning · Computer Science 2024-08-08 Shanshan Wu , Zheng Xu , Yanxiang Zhang , Yuanbo Zhang , Daniel Ramage

In the low-data regime, it is difficult to train good supervised models from scratch. Instead practitioners turn to pre-trained models, leveraging transfer learning. Ensembling is an empirically and theoretically appealing way to construct…

Machine Learning · Computer Science 2020-10-20 Basil Mustafa , Carlos Riquelme , Joan Puigcerver , André Susano Pinto , Daniel Keysers , Neil Houlsby

Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Saurabh Kataria , Jesús Villalba , Najim Dehak

Large language models (LMs) have rapidly become a mainstay in Natural Language Processing. These models are known to acquire rich linguistic knowledge from training on large amounts of text. In this paper, we investigate if pre-training on…

Computation and Language · Computer Science 2022-10-25 Avinash Madasu , Shashank Srivastava

Large Transformer-based language models are pre-trained on corpora of varying sizes, for a different number of steps and with different batch sizes. At the same time, more fundamental components, such as the pre-training objective or…

Computation and Language · Computer Science 2021-05-12 M. Aßenmacher , P. Schulze , C. Heumann

Previous language model pre-training methods have uniformly applied a next-token prediction loss to all training tokens. Challenging this norm, we posit that "9l training". Our initial analysis examines token-level training dynamics of…

Computation and Language · Computer Science 2025-01-09 Zhenghao Lin , Zhibin Gou , Yeyun Gong , Xiao Liu , Yelong Shen , Ruochen Xu , Chen Lin , Yujiu Yang , Jian Jiao , Nan Duan , Weizhu Chen

Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over…

Computation and Language · Computer Science 2021-09-16 Rongzhou Bao , Zhuosheng Zhang , Hai Zhao