English
Related papers

Related papers: Reusing Overtrained Language Models Saturates Scal…

200 papers

The success of pretrained cross-lingual language models relies on two essential abilities, i.e., generalization ability for learning downstream tasks in a source language, and cross-lingual transferability for transferring the task…

Computation and Language · Computer Science 2021-09-24 Zewen Chi , Heyan Huang , Luyang Liu , Yu Bai , Xian-Ling Mao

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Computation and Language · Computer Science 2021-04-15 Nikunj Saunshi , Sadhika Malladi , Sanjeev Arora

In recent years, Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence. However, training these models from scratch requires substantial computational resources and vast amounts of text data. In…

Computation and Language · Computer Science 2024-10-03 Wenzhen Zheng , Wenbo Pan , Xu Xu , Libo Qin , Li Yue , Ming Zhou

Molecular generative models, often employing GPT-style language modeling on molecular string representations, have shown promising capabilities when scaled to large datasets and model sizes. However, it remains unclear and subject to debate…

Machine Learning · Computer Science 2026-02-02 Dong Xu , Qihua Pan , Sisi Yuan , Jianqiang Li , Zexuan Zhu , Junkai Ji

Scaling issues are mundane yet irritating for practitioners of reinforcement learning. Error scales vary across domains, tasks, and stages of learning; sometimes by many orders of magnitude. This can be detrimental to learning speed and…

Machine Learning · Computer Science 2021-05-13 Tom Schaul , Georg Ostrovski , Iurii Kemaev , Diana Borsa

Multilinguality is crucial for extending recent advancements in language modelling to diverse linguistic communities. To maintain high performance while representing multiple languages, multilingual models ideally align representations,…

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

Test-Time Scaling enhances the reasoning capabilities of Large Language Models by allocating additional inference compute to broaden the exploration of the solution space. However, existing search strategies typically treat rollouts as…

Computation and Language · Computer Science 2026-05-06 Xinglin Wang , Jiayi Shi , Shaoxiong Feng , Peiwen Yuan , Yiwei Li , Yueqi Zhang , Chuyi Tan , Ji Zhang , Boyuan Pan , Yao Hu , Kan Li

In this work, we provide a large-scale empirical study of the scaling properties of multilingual neural machine translation models. We examine how increases in the model size affect the model performance and investigate the role of the…

Computation and Language · Computer Science 2023-02-21 Patrick Fernandes , Behrooz Ghorbani , Xavier Garcia , Markus Freitag , Orhan Firat

We present an efficient method of utilizing pretrained language models, where we learn selective binary masks for pretrained weights in lieu of modifying them through finetuning. Extensive evaluations of masking BERT and RoBERTa on a series…

Computation and Language · Computer Science 2020-10-13 Mengjie Zhao , Tao Lin , Fei Mi , Martin Jaggi , Hinrich Schütze

We provide an empirical investigation of the potential of pre-training vision-language models on an unprecedented scale: 100 billion examples. We find that model performance tends to saturate at this scale on many common Western-centric…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Xiao Wang , Ibrahim Alabdulmohsin , Daniel Salz , Zhe Li , Keran Rong , Xiaohua Zhai

Parameter-efficient methods are able to use a single frozen pre-trained large language model (LLM) to perform many tasks by learning task-specific soft prompts that modulate model behavior when concatenated to the input text. However, these…

Computation and Language · Computer Science 2022-08-12 Brian Lester , Joshua Yurtsever , Siamak Shakeri , Noah Constant

Large language models learn from their vast pre-training corpora, gaining the ability to solve an ever increasing variety of tasks; yet although researchers work to improve these datasets, there is little effort to understand how efficient…

Computation and Language · Computer Science 2025-11-07 Alex Fang , Thomas Voice , Ruoming Pang , Ludwig Schmidt , Tom Gunter

Multilingual models are often particularly dependent on scaling to generalize to a growing number of languages. Compression techniques are widely relied upon to reconcile the growth in model size with real world resource constraints, but…

Computation and Language · Computer Science 2022-11-29 Kelechi Ogueji , Orevaoghene Ahia , Gbemileke Onilude , Sebastian Gehrmann , Sara Hooker , Julia Kreutzer

Continual learning aims to enable models to adapt to new datasets without losing performance on previously learned data, often assuming that prior data is no longer available. However, in many practical scenarios, both old and new data are…

Machine Learning · Computer Science 2025-03-03 Eli Verwimp , Guy Hacohen , Tinne Tuytelaars

While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We investigate whether one could make a task-specific selection on…

Computation and Language · Computer Science 2022-10-20 Shuo Xie , Jiahao Qiu , Ankita Pasad , Li Du , Qing Qu , Hongyuan Mei

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…

Computation and Language · Computer Science 2026-05-20 Bowen Peng , Théo Gigant , Jeffrey Quesnelle

Scaling model size, training data, and compute power have driven advances in large language models (LLMs), but these approaches are reaching saturation as human-generated text is exhausted and further gains diminish. We propose experience…

Artificial Intelligence · Computer Science 2025-09-24 Xingkun Yin , Kaibin Huang , Dong In Kim , Hongyang Du

Large-scale models for learning fixed-dimensional cross-lingual sentence representations like LASER (Artetxe and Schwenk, 2019b) lead to significant improvement in performance on downstream tasks. However, further increases and…

Computation and Language · Computer Science 2022-05-30 Zhuoyuan Mao , Prakhar Gupta , Pei Wang , Chenhui Chu , Martin Jaggi , Sadao Kurohashi

Adapting pre-trained models to specialized tasks often leads to catastrophic forgetting, where new knowledge overwrites foundational capabilities. Existing methods either compromise performance on the new task or struggle to balance…

Machine Learning · Computer Science 2026-03-10 Dyah Adila , Hanna Mazzawi , Benoit Dherin , Xavier Gonzalvo

The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a…

Computation and Language · Computer Science 2026-03-24 Hadi Pouransari , David Grangier , C Thomas , Michael Kirchhof , Oncel Tuzel