English
Related papers

Related papers: How Can We Synthesize High-Quality Pretraining Dat…

200 papers

Training data plays a crucial role in Large Language Models (LLM) scaling, yet high quality data is of limited supply. Synthetic data techniques offer a potential path toward sidestepping these limitations. We conduct a large-scale…

Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study how to design synthetic data algorithms that achieve better loss scaling: not only lowering loss at…

Machine Learning · Computer Science 2026-03-20 Konwoo Kim , Suhas Kotha , Yejin Choi , Tatsunori Hashimoto , Nick Haber , Percy Liang

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Machine Learning · Computer Science 2025-10-28 Amal Abed , Ivan Lukic , Jörg K. H. Franke , Frank Hutter

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…

This survey reviews how large language models (LLMs) are transforming synthetic training data generation in both natural language and code domains. By producing artificial but task-relevant examples, these models can significantly augment…

Computation and Language · Computer Science 2025-11-21 Mihai Nadas , Laura Diosan , Andreea Tomescu

Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of…

Artificial Intelligence · Computer Science 2026-01-13 Gabriela Ben Melech Stan , Estelle Aflalo , Avinash Madasu , Vasudev Lal , Phillip Howard

Recently published work on rephrasing natural text data for pre-training LLMs has shown promising results when combining the original dataset with the synthetically rephrased data. We build upon previous work by replicating existing results…

The impressive capabilities of recent language models can be largely attributed to the multi-trillion token pretraining datasets that they are trained on. However, model developers fail to disclose their construction methodology which has…

Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic data will fundamentally reshape the web data ecosystem.…

Computation and Language · Computer Science 2025-05-29 Xuekai Zhu , Daixuan Cheng , Hengli Li , Kaiyan Zhang , Ermo Hua , Xingtai Lv , Ning Ding , Zhouhan Lin , Zilong Zheng , Bowen Zhou

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-21 Vahid Noroozi , Zhehuai Chen , Somshubra Majumdar , Steve Huang , Jagadeesh Balam , Boris Ginsburg

Large language models can perform various reasoning tasks by using chain-of-thought prompting, which guides them to find answers through step-by-step demonstrations. However, the quality of the prompts depends on the demonstrations given to…

Computation and Language · Computer Science 2023-02-02 Zhihong Shao , Yeyun Gong , Yelong Shen , Minlie Huang , Nan Duan , Weizhu Chen

Natural Language Processing (NLP) has undergone transformative changes with the advent of deep learning methodologies. One challenge persistently confronting researchers is the scarcity of high-quality, annotated datasets that drive these…

Computation and Language · Computer Science 2023-10-13 Sia Gholami , Marwan Omar

Despite recent advances in large language models, building dependable and deployable NLP models typically requires abundant, high-quality training data. However, task-specific data is not available for many use cases, and manually curating…

Computation and Language · Computer Science 2024-04-30 Saumya Gandhi , Ritu Gala , Vijay Viswanathan , Tongshuang Wu , Graham Neubig

Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on…

Computation and Language · Computer Science 2024-06-19 Jie Chen , Yupeng Zhang , Bingning Wang , Wayne Xin Zhao , Ji-Rong Wen , Weipeng Chen

Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation. Despite these benefits, the efficiency of…

Machine Learning · Computer Science 2024-03-21 Jianhao Yuan , Jie Zhang , Shuyang Sun , Philip Torr , Bo Zhao

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

Computation and Language · Computer Science 2024-01-09 Jean Kaddour , Qi Liu

The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation. However, the growth rate of high-quality data is significantly outpaced by the…

Computation and Language · Computer Science 2024-10-18 Ke Wang , Jiahui Zhu , Minjie Ren , Zeming Liu , Shiwei Li , Zongye Zhang , Chenkai Zhang , Xiaoyu Wu , Qiqi Zhan , Qingjie Liu , Yunhong Wang

We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a neural network using synthetic data can be viewed as…

Machine Learning · Computer Science 2017-03-03 Tuan Anh Le , Atilim Gunes Baydin , Robert Zinkov , Frank Wood

This study pioneers the use of synthetically generated data for training generative models in document-level text simplification of German texts. We demonstrate the effectiveness of our approach with real-world online texts. Addressing the…

Computation and Language · Computer Science 2024-02-19 Lars Klöser , Mika Beele , Jan-Niklas Schagen , Bodo Kraft

Large language models are trained on massive scrapes of the web, which are often unstructured, noisy, and poorly phrased. Current scaling laws show that learning from such data requires an abundance of both compute and data, which grows…

Computation and Language · Computer Science 2024-01-30 Pratyush Maini , Skyler Seto , He Bai , David Grangier , Yizhe Zhang , Navdeep Jaitly
‹ Prev 1 2 3 10 Next ›