中文
相关论文

相关论文: ScalingFilter: Assessing Data Quality through Inve…

200 篇论文

Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is Classifier-based Quality Filtering (CQF), which trains a binary classifier to…

机器学习 · 计算机科学 2025-10-03 Thiziri Nait Saada , Louis Bethune , Michal Klein , David Grangier , Marco Cuturi , Pierre Ablin

Scaling laws for language model training traditionally characterize how performance scales with model size and dataset volume. Prior work has explored architecture variants and data treatments such as dataset filtering and noise injection…

机器学习 · 计算机科学 2026-02-24 Anirudh Subramanyam , Yuxin Chen , Robert L. Grossman

Traditional scaling laws in natural language processing suggest that increasing model size and training data enhances performance. However, recent studies reveal deviations, particularly in large language models, where performance…

机器学习 · 计算机科学 2025-07-16 Zhengyu Chen , Siqi Wang , Teng Xiao , Yudong Wang , Shiqi Chen , Xunliang Cai , Junxian He , Jingang Wang

Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this…

We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a cost-efficient way to estimate the quality of data sources (e.g. synthetically generated or filtered web…

The performance of large language models (LLMs) is strongly influenced by the quality and diversity of data used during supervised fine-tuning (SFT). However, current data selection methods often prioritize one aspect over the other,…

计算与语言 · 计算机科学 2025-05-28 Minghao Wu , Thuy-Trang Vu , Lizhen Qu , Gholamreza Haffari

Scaling laws predict that the performance of large language models improves with increasing model size and data size. In practice, pre-training has been relying on massive web crawls, using almost all data sources publicly available on the…

计算与语言 · 计算机科学 2025-09-16 Thao Nguyen , Yang Li , Olga Golovneva , Luke Zettlemoyer , Sewoong Oh , Ludwig Schmidt , Xian Li

Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are…

When selecting data for training large-scale models, standard practice is to filter for examples that match human notions of data quality. Such filtering yields qualitatively clean datapoints that intuitively should improve model behavior.…

机器学习 · 计算机科学 2024-01-24 Logan Engstrom , Axel Feldmann , Aleksander Madry

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that…

计算与语言 · 计算机科学 2024-12-10 Tingyu Xia , Bowen Yu , Kai Dang , An Yang , Yuan Wu , Yuan Tian , Yi Chang , Junyang Lin

Data quality is a key element for building and optimizing good learning models. Despite many attempts to characterize data quality, there is still a need for rigorous formalization and an efficient measure of the quality from available…

机器学习 · 计算机科学 2023-12-14 Jouseau Roxane , Salva Sébastien , Samir Chafik

The composition of pre-training datasets for large language models (LLMs) remains largely undisclosed, hindering transparency and efforts to optimize data quality, a critical driver of model performance. Current data selection methods, such…

计算与语言 · 计算机科学 2025-08-07 Xinlin Zhuang , Jiahui Peng , Ren Ma , Yinfan Wang , Tianyi Bai , Xingjian Wei , Jiantao Qiu , Chi Zhang , Ying Qian , Conghui He

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…

机器学习 · 计算机科学 2026-05-18 Anastasiia Sedova , Skyler Seto , Natalie Schluter , Pierre Ablin

Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle…

计算与语言 · 计算机科学 2025-06-02 Xiaoqing Cheng , Ruizhe Chen , Hongying Zan , Yuxiang Jia , Min Peng

Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly between languages as prior works show that adding more languages…

计算与语言 · 计算机科学 2025-06-17 Skyler Seto , Maartje ter Hoeve , Maureen de Seyssel , David Grangier

In studies of transferable learning, scaling laws are obtained for various important foundation models to predict their properties and performance at larger scales. We show here how scaling law derivation can also be used for model and…

Large language models have demonstrated remarkable capabilities across various tasks, primarily attributed to the utilization of diversely sourced data. However, the impact of pretraining data composition on model performance remains poorly…

机器学习 · 计算机科学 2025-01-28 Ce Ge , Zhijian Ma , Daoyuan Chen , Yaliang Li , Bolin Ding

Finetuning large language models on instruction data is crucial for enhancing pre-trained knowledge and improving instruction-following capabilities. As instruction datasets proliferate, selecting optimal data for effective training becomes…

计算与语言 · 计算机科学 2024-09-18 Simon Yu , Liangyu Chen , Sara Ahmadian , Marzieh Fadaee

Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models…

计算与语言 · 计算机科学 2024-02-21 Ruibo Chen , Yihan Wu , Lichang Chen , Guodong Liu , Qi He , Tianyi Xiong , Chenxi Liu , Junfeng Guo , Heng Huang

Scaling laws provide important insights that can guide the design of large language models (LLMs). Existing work has primarily focused on studying scaling laws for pretraining (upstream) loss. However, in transfer learning settings, in…

计算与语言 · 计算机科学 2026-01-30 Berivan Isik , Natalia Ponomareva , Hussein Hazimeh , Dimitris Paparas , Sergei Vassilvitskii , Sanmi Koyejo
‹ 上一页 1 2 3 10 下一页 ›