English
Related papers

Related papers: Language Models Improve When Pretraining Data Matc…

200 papers

Modern ASR systems are typically trained on large-scale pseudo-labeled, in-the-wild data spanning multiple domains. While such heterogeneous data benefit generalist models designed for broad deployment, they pose challenges for specialist…

The data mixture for large language model pre-training significantly impacts performance, yet how to determine an effective mixture remains unclear. We propose RegMix to automatically identify a high-performing data mixture by formulating…

Computation and Language · Computer Science 2025-01-24 Qian Liu , Xiaosen Zheng , Niklas Muennighoff , Guangtao Zeng , Longxu Dou , Tianyu Pang , Jing Jiang , Min Lin

The introduction of pre-trained language models has revolutionized natural language research communities. However, researchers still know relatively little regarding their theoretical and empirical properties. In this regard, Peters et al.…

Computation and Language · Computer Science 2019-07-12 Ran Wang , Haibo Su , Chunye Wang , Kailin Ji , Jupeng Ding

This is the second year of the TREC Deep Learning Track, with the goal of studying ad hoc ranking in the large training data regime. We again have a document retrieval task and a passage retrieval task, each with hundreds of thousands of…

Information Retrieval · Computer Science 2021-02-16 Nick Craswell , Bhaskar Mitra , Emine Yilmaz , Daniel Campos

Large language models (LLMs) have demonstrated outstanding performance in natural language processing tasks. However, in the field of recommender systems, due to the inherent structural discrepancy between user behavior data and natural…

Information Retrieval · Computer Science 2026-01-01 Zekun Liu , Xiaowen Huang , Jitao Sang

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Machine Learning · Computer Science 2025-10-01 Animesh Jha , Harshit Gupta , Ananjan Nandi

Word vectors and Language Models (LMs) pretrained on a large amount of unlabelled data can dramatically improve various Natural Language Processing (NLP) tasks. However, the measure and impact of similarity between pretraining data and…

Computation and Language · Computer Science 2019-05-20 Xiang Dai , Sarvnaz Karimi , Ben Hachey , Cecile Paris

This study aims at improving the performance of scoring student responses in science education automatically. BERT-based language models have shown significant superiority over traditional NLP models in various language-related tasks.…

Artificial Intelligence · Computer Science 2023-11-21 Zhengliang Liu , Xinyu He , Lei Liu , Tianming Liu , Xiaoming Zhai

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we…

Computation and Language · Computer Science 2019-07-29 Yinhan Liu , Myle Ott , Naman Goyal , Jingfei Du , Mandar Joshi , Danqi Chen , Omer Levy , Mike Lewis , Luke Zettlemoyer , Veselin Stoyanov

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

Pretraining NLP models with variants of Masked Language Model (MLM) objectives has recently led to a significant improvements on many tasks. This paper examines the benefits of pretrained models as a function of the number of training…

Computation and Language · Computer Science 2020-06-17 Sinong Wang , Madian Khabsa , Hao Ma

An effective ranking model usually requires a large amount of training data to learn the relevance between documents and queries. User clicks are often used as training data since they can indicate relevance and are cheap to collect, but…

Information Retrieval · Computer Science 2023-02-21 Xiaojie Sun , Lulu Yu , Yiting Wang , Keping Bi , Jiafeng Guo

Fueled by their remarkable ability to tackle diverse tasks across multiple domains, large language models (LLMs) have grown at an unprecedented rate, with some recent models containing trillions of parameters. This growth is accompanied by…

Machine Learning · Computer Science 2025-05-30 Athanasios Glentis , Jiaxiang Li , Qiulin Shang , Andi Han , Ioannis Tsaknakis , Quan Wei , Mingyi Hong

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on…

Computation and Language · Computer Science 2021-06-07 Inigo Jauregi Unanue , Jacob Parnell , Massimo Piccardi

Continual pre-training is widely used to adapt LLMs to target languages and domains, yet the mixture ratio of training data remains a sensitive hyperparameter that is expensive to tune: they must be fixed before training begins, and a…

Computation and Language · Computer Science 2026-04-07 Haiyue Song , Masao Utiyama

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…

Computation and Language · Computer Science 2023-05-29 Kundan Krishna , Saurabh Garg , Jeffrey P. Bigham , Zachary C. Lipton

Pretraining large language models effectively requires strategic data selection, blending and ordering. However, key details about data mixtures especially their scalability to longer token horizons and larger model sizes remain…

Computation and Language · Computer Science 2024-12-23 Steven Feng , Shrimai Prabhumoye , Kezhi Kong , Dan Su , Mostofa Patwary , Mohammad Shoeybi , Bryan Catanzaro

For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield…

Machine Learning · Computer Science 2020-12-02 Pascal Sturmfels , Jesse Vig , Ali Madani , Nazneen Fatema Rajani

Product ranking is a crucial component for many e-commerce services. One of the major challenges in product search is the vocabulary mismatch between query and products, which may be a larger vocabulary gap problem compared to other…

Information Retrieval · Computer Science 2022-04-04 Xuyang Wu , Alessandro Magnani , Suthee Chaidaroon , Ajit Puthenputhussery , Ciya Liao , Yi Fang

The increasing size and complexity of pre-trained language models have demonstrated superior performance in many applications, but they usually require large training datasets to be adequately trained. Insufficient training sets could…

Computation and Language · Computer Science 2025-02-03 Yaping Chai , Haoran Xie , Joe S. Qin