English
Related papers

Related papers: Scale Dependent Data Duplication

200 papers

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate…

Machine Learning · Statistics 2026-02-05 Kazuto Fukuchi , Ryuichiro Hataya , Kota Matsui

Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks. Yet such laws are most needed precisely where they are…

Machine Learning · Computer Science 2026-05-11 Xing Han , Ziyin Liu , Suchi Saria , Paul Pu Liang

The current trend of scaling language models involves increasing both parameter count and training dataset size. Extrapolating this trend suggests that training dataset size may soon be limited by the amount of text data available on the…

Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast approximate nearest neighbor algorithms. As the tasks dense…

Information Retrieval · Computer Science 2026-02-06 Julian Killingback , Mahta Rafiee , Madine Manas , Hamed Zamani

Data filtering has become a powerful tool for improving model performance while reducing computational cost. However, as large language model compute budgets continue to grow, the limited data volume provided by heavily filtered and…

Computation and Language · Computer Science 2025-11-07 Alex Fang , Hadi Pouransari , Matt Jordan , Alexander Toshev , Vaishaal Shankar , Ludwig Schmidt , Tom Gunter

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

Multilingual large language models achieve impressive cross-lingual performance despite largely monolingual pretraining. While bilingual data in pretraining corpora is widely believed to enable these abilities, details of its contributions…

Computation and Language · Computer Science 2026-01-26 Jiandong Shao , Raphael Tang , Crystina Zhang , Karin Sevegnani , Pontus Stenetorp , Jianfei Yang , Yao Lu

Large language models (LMs) are currently trained to predict tokens given document prefixes, enabling them to directly perform long-form generation and prompting-style tasks which can be reduced to document completion. Existing pretraining…

Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities might arise from evaluation datasets being included in the…

Computation and Language · Computer Science 2024-01-12 Minhao Jiang , Ken Ziyu Liu , Ming Zhong , Rylan Schaeffer , Siru Ouyang , Jiawei Han , Sanmi Koyejo

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.…

Computation and Language · Computer Science 2022-10-20 Malte Ostendorff , Nils Rethmeier , Isabelle Augenstein , Bela Gipp , Georg Rehm

Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data…

Cryptography and Security · Computer Science 2025-07-17 Dayong Ye , Tianqing Zhu , Jiayang Li , Kun Gao , Bo Liu , Leo Yu Zhang , Wanlei Zhou , Yang Zhang

Choice of training data distribution greatly influences model behavior. Yet, in large-scale settings, precisely characterizing how changes in training data affects predictions is often difficult due to model training costs. Current practice…

Machine Learning · Computer Science 2025-05-23 Alaa Khaddaj , Logan Engstrom , Aleksander Madry

Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web…

Computation and Language · Computer Science 2023-09-12 Max Marion , Ahmet Üstün , Luiza Pozzobon , Alex Wang , Marzieh Fadaee , Sara Hooker

Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise "precision-aware" scaling laws for both training and inference. We propose…

Masked Language Modeling (MLM) pre-training is one of the primary ways to initialize Neural Information Retrieval (IR) models prior to retrieval fine-tuning. However, studies show that MLM pre-trained models have limited readiness and…

Information Retrieval · Computer Science 2026-05-05 Hiun Kim , Tae Kwan Lee , Taeryun Won

Tokenisation is a core part of language models (LMs). It involves splitting a character sequence into subwords which are assigned arbitrary indices before being served to the LM. While typically lossless, however, this process may lead to…

Computation and Language · Computer Science 2024-07-18 Anton Schäfer , Thomas Hofmann , Imanol Schlag , Tiago Pimentel

We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual pretraining. A primary challenge in studying multilingual…

Computation and Language · Computer Science 2024-12-05 Yifei He , Alon Benhaim , Barun Patra , Praneetha Vaddamanu , Sanchit Ahuja , Parul Chopra , Vishrav Chaudhary , Han Zhao , Xia Song

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…

Computation and Language · Computer Science 2024-10-07 Ernie Chang , Matteo Paltenghi , Yang Li , Pin-Jie Lin , Changsheng Zhao , Patrick Huber , Zechun Liu , Rastislav Rabatin , Yangyang Shi , Vikas Chandra

Domain-adaptive pretraining (DAPT) offers a practical path to specializing large language models for high-value domains without full retraining. We conduct an early-stage scaling-law analysis of continued pretraining on U.S. SEC filings,…

Machine Learning · Computer Science 2025-12-16 Jesse Ponnock

Within the scaling laws paradigm, which underpins the training of large neural networks like ChatGPT and Llama, we consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon, a…

Machine Learning · Computer Science 2024-10-10 Elvis Dohmatob , Yunzhen Feng , Arjun Subramonian , Julia Kempe