English
Related papers

Related papers: Optimizing Pre-Training Data Mixtures with Mixture…

200 papers

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data…

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made…

Machine Learning · Computer Science 2025-10-17 Ruijie Miao , Yilun Yao , Zihan Wang , Zhiming Wang , Bairen Yi , LingJun Liu , Yikai Zhao , Tong Yang

Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text embedding models in a compute-optimal fashion, given a suite…

Machine Learning · Computer Science 2024-11-22 Alicja Ziarko , Albert Q. Jiang , Bartosz Piotrowski , Wenda Li , Mateja Jamnik , Piotr Miłoś

Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models. The diversity of the data distributions and cost of joint training makes the optimization procedure extremely…

Computation and Language · Computer Science 2024-11-06 Dhananjay Ram , Aditya Rawal , Momchil Hardalov , Nikolaos Pappas , Sheng Zha

Mixture models trained via EM are among the simplest, most widely used and well understood latent variable models in the machine learning literature. Surprisingly, these models have been hardly explored in text generation applications such…

Computation and Language · Computer Science 2019-05-27 Tianxiao Shen , Myle Ott , Michael Auli , Marc'Aurelio Ranzato

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

Computation and Language · Computer Science 2025-12-09 Sebastian Sztwiertnia , Felix Friedrich , Kristian Kersting , Patrick Schramowski , Björn Deiseroth

A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard…

Computation and Language · Computer Science 2024-05-31 Xudong Lu , Qi Liu , Yuhui Xu , Aojun Zhou , Siyuan Huang , Bo Zhang , Junchi Yan , Hongsheng Li

Cross-entropy loss is a common choice when it comes to multiclass classification tasks and language modeling in particular. Minimizing this loss results in language models of very good quality. We show that it is possible to fine-tune these…

Computation and Language · Computer Science 2019-01-16 Vadim Popov , Mikhail Kudinov

Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate cross-lingual transfer of multilingual pretrained models…

Computation and Language · Computer Science 2021-09-13 Xinyi Wang , Yulia Tsvetkov , Sebastian Ruder , Graham Neubig

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization…

Networking and Internet Architecture · Computer Science 2024-02-16 Hongyang Du , Guangyuan Liu , Yijing Lin , Dusit Niyato , Jiawen Kang , Zehui Xiong , Dong In Kim

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Machine Learning · Computer Science 2024-04-09 Bowen Pan , Yikang Shen , Haokun Liu , Mayank Mishra , Gaoyuan Zhang , Aude Oliva , Colin Raffel , Rameswar Panda

Mixture-of-Expert (MoE) based large language models (LLMs), such as the recent Mixtral and DeepSeek-MoE, have shown great promise in scaling model size without suffering from the quadratic growth of training cost of dense transformers. Like…

Machine Learning · Computer Science 2024-04-04 Longfei Yun , Yonghao Zhuang , Yao Fu , Eric P Xing , Hao Zhang

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant…

Machine Learning · Computer Science 2026-03-03 Qian Chen , Xianhao Chen , Kaibin Huang

Large language models are trained on massive scrapes of the web, as required by current scaling laws. Most progress is made for English, given its abundance of high-quality pretraining data. For most other languages, however, such high…

Computation and Language · Computer Science 2025-02-07 Skyler Seto , Maartje ter Hoeve , Richard He Bai , Natalie Schluter , David Grangier

Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-specific model merging. In this work, we test whether merging can be applied to monolingually…

Computation and Language · Computer Science 2026-05-26 Seth Aycock , Fedor Vitiugin , Aleksandr Umnov , Christof Monz , Khalil Sima'an

Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the final model remains poorly understood. Notably, although…

In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…

Machine Learning · Computer Science 2020-10-07 Cameron R. Wolfe , Keld T. Lundgaard

Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter…

Computation and Language · Computer Science 2026-05-26 Bo Li , Tianyu Dong , Shaolin Zhu , Deyi Xiong

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