English
Related papers

Related papers: Pretraining with hierarchical memories: separating…

200 papers

Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as $\mu$P, have enabled transfer of optimal global hyperparameters across…

Machine Learning · Computer Science 2025-12-30 Bruno Mlodozeniec , Pierre Ablin , Louis Béthune , Dan Busbridge , Michal Klein , Jason Ramapuram , Marco Cuturi

In this work, we investigate how a model's tendency to broadly integrate its parametric knowledge evolves throughout pretraining, and how this behavior affects overall performance, particularly in terms of knowledge acquisition and…

Computation and Language · Computer Science 2025-03-13 Jiyeon Kim , Hyunji Lee , Hyowon Cho , Joel Jang , Hyeonbin Hwang , Seungpil Won , Youbin Ahn , Dohaeng Lee , Minjoon Seo

Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across model sizes and…

Computation and Language · Computer Science 2022-11-04 Kushal Tirumala , Aram H. Markosyan , Luke Zettlemoyer , Armen Aghajanyan

Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the…

The memory subsystem has always been a bottleneck in performance as well as significant power contributor in memory intensive applications. Many researchers have presented multi-layered memory hierarchies as a means to design energy and…

Hardware Architecture · Computer Science 2011-11-09 Minas Dasygenis , Erik Brockmeyer , Bart Durinck , Francky Catthoor , Dimitrios Soudris , Antonios Thanailakis

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

Computation and Language · Computer Science 2023-06-01 Aaron Mueller , Tal Linzen

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an…

Computation and Language · Computer Science 2025-02-26 Fangyuan Yu

Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…

Computation and Language · Computer Science 2023-06-13 Jonas Wallat , Tianyi Zhang , Avishek Anand

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

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…

Machine Learning · Computer Science 2026-05-08 Yazheng Liu , Yuxuan Wan , Rui Xu , Xi Zhang , Sihong Xie , Hui Xiong

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequences while freezing the…

Computation and Language · Computer Science 2023-05-26 Jonathan Li , Will Aitken , Rohan Bhambhoria , Xiaodan Zhu

The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory hierarchy of the human brain, we reduce this cost by…

Computation and Language · Computer Science 2025-01-29 Hongkang Yang , Zehao Lin , Wenjin Wang , Hao Wu , Zhiyu Li , Bo Tang , Wenqiang Wei , Jinbo Wang , Zeyun Tang , Shichao Song , Chenyang Xi , Yu Yu , Kai Chen , Feiyu Xiong , Linpeng Tang , Weinan E

Large language models (LLMs) have demonstrated remarkable progress in leveraging diverse knowledge sources. This study investigates how nine widely used LLMs allocate knowledge between local context and global parameters when answering…

Computation and Language · Computer Science 2024-11-22 Yufei Tao , Adam Hiatt , Erik Haake , Antonie J. Jetter , Ameeta Agrawal

Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling. To continue scaling pretraining in this data-constrained regime, we…

Machine Learning · Computer Science 2025-09-30 Yangjun Ruan , Neil Band , Chris J. Maddison , Tatsunori Hashimoto

Large language models may encounter factual knowledge during pre-training yet fail to reliably use that knowledge after fine-tuning. Despite growing empirical evidence that MLP layers store factual associations and fine-tuning affects…

Machine Learning · Computer Science 2026-05-19 Ruichen Xu , Kexin Chen

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

Computation and Language · Computer Science 2024-10-10 Bozhou Li , Hao Liang , Yang Li , Fangcheng Fu , Hongzhi Yin , Conghui He , Wentao Zhang

State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…

Computation and Language · Computer Science 2020-04-30 Evani Radiya-Dixit , Xin Wang

Large language models are powerful but costly. We ask whether meta-learning can make the pretraining of small language models not only better but also more interpretable. We integrate first-order MAML with subset-masked LM pretraining,…

Computation and Language · Computer Science 2025-11-10 David Demitri Africa , Yuval Weiss , Paula Buttery , Richard Diehl Martinez