English
Related papers

Related papers: Cabrita: closing the gap for foreign languages

200 papers

Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and…

Computation and Language · Computer Science 2024-05-14 Cagri Toraman

The popularity of LLaMA (Touvron et al., 2023a;b) and other recently emerged moderate-sized large language models (LLMs) highlights the potential of building smaller yet powerful LLMs. Regardless, the cost of training such models from…

Computation and Language · Computer Science 2024-04-12 Mengzhou Xia , Tianyu Gao , Zhiyuan Zeng , Danqi Chen

Large language models are pre-trained on ever-growing token budgets under the assumption that better pre-training performance translates to improved downstream models. In this work, we challenge this assumption and show that extended…

Computation and Language · Computer Science 2025-03-31 Jacob Mitchell Springer , Sachin Goyal , Kaiyue Wen , Tanishq Kumar , Xiang Yue , Sadhika Malladi , Graham Neubig , Aditi Raghunathan

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

Large language models have led to state-of-the-art accuracies across a range of tasks. However,training large language model needs massive computing resource, as more and more open source pre-training models are available, it is worthy to…

Computation and Language · Computer Science 2021-04-26 Han Zhang

Continual pre-training has increasingly become the predominant approach for adapting Large Language Models (LLMs) to new domains. This process involves updating the pre-trained LLM with a corpus from a new domain, resulting in a shift in…

Computation and Language · Computer Science 2024-06-28 Yiduo Guo , Jie Fu , Huishuai Zhang , Dongyan Zhao , Yikang Shen

In this work, we explore how to train task-specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models…

Computation and Language · Computer Science 2022-07-12 Mayank Kulkarni , Debanjan Mahata , Ravneet Arora , Rajarshi Bhowmik

Large Language Models (LLMs) have played an important role in many fields due to their powerful capabilities.However, their massive number of parameters leads to high deployment requirements and incurs significant inference costs, which…

In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Yuan Liu , Zhongyin Zhao , Ziyuan Zhuang , Le Tian , Xiao Zhou , Jie Zhou

Small Language Models (SLMs) enable cost-effective, on-device and latency-sensitive AI applications, yet their deployment in Traditional Chinese (TC) remains hindered by token-level instability - models unpredictably emit non-TC characters…

Computation and Language · Computer Science 2025-10-03 Yu-Cheng Chih , Ming-Tao Duan , Yong-Hao Hou

Large language models can be quantized to reduce inference time latency, model size, and energy consumption, thereby delivering a better user experience at lower cost. A challenge exists to deliver quantized models with minimal loss of…

Machine Learning · Computer Science 2025-07-24 Steven K. Esser , Jeffrey L. McKinstry , Deepika Bablani , Rathinakumar Appuswamy , Dharmendra S. Modha

The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, RoBERTa, and GPT-2 require a huge compute budget to create a…

Computation and Language · Computer Science 2021-04-21 Luca Di Liello , Matteo Gabburo , Alessandro Moschitti

Tokenizer adaptation plays an important role in adapting pre-trained language models to new domains or languages. In this work, we address two complementary aspects of this process: vocabulary extension and pruning. The common approach to…

Computation and Language · Computer Science 2026-03-24 Taido Purason , Pavel Chizhov , Ivan P. Yamshchikov , Mark Fishel

While Large Language Models (LLMs) have shown remarkable capabilities in natural language understanding and generation, their performance often lags in lower-resource, non-English languages due to biases in the training data. In this work,…

Computation and Language · Computer Science 2024-12-11 Matthieu Meeus , Anthony Rathé , François Remy , Pieter Delobelle , Jens-Joris Decorte , Thomas Demeester

We explore how continued pre-training on domain-specific corpora influences large language models, revealing that training on the raw corpora endows the model with domain knowledge, but drastically hurts its prompting ability for question…

Computation and Language · Computer Science 2024-07-26 Daixuan Cheng , Shaohan Huang , Furu Wei

The prohibitive training costs of Large Language Models (LLMs) have emerged as a significant bottleneck in the development of next-generation LLMs. In this paper, we show that it is possible to significantly reduce the training costs of…

Computation and Language · Computer Science 2025-05-16 Chenze Shao , Fandong Meng , Jie Zhou

ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model. Although ELECTRA offers a significant boost in efficiency, its potential is constrained by the training cost brought by the…

Computation and Language · Computer Science 2023-10-12 Chengyu Dong , Liyuan Liu , Hao Cheng , Jingbo Shang , Jianfeng Gao , Xiaodong Liu

The high compute cost associated with pretraining large language models limits their research. Two strategies have emerged to address this issue: domain specialization and pretraining with high-quality data. To explore these strategies, we…

Computation and Language · Computer Science 2025-07-29 Roseval Malaquias Junior , Ramon Pires , Roseli Romero , Rodrigo Nogueira

This paper presents a comprehensive study on the tokenization techniques employed by state-of-the-art large language models (LLMs) and their implications on the cost and availability of services across different languages, especially low…

Computation and Language · Computer Science 2024-10-07 Abrar Rahman , Garry Bowlin , Binit Mohanty , Sean McGunigal

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