English
Related papers

Related papers: Data Mixture Inference: What do BPE Tokenizers Rev…

200 papers

Tokenizers act as a bridge between human language and the latent space of language models, influencing how language is represented in these models. Due to the immense popularity of English-Centric Large Language Models (LLMs), efforts are…

Computation and Language · Computer Science 2025-01-22 Menan Velayuthan , Kengatharaiyer Sarveswaran

The effectiveness of Neural Machine Translation (NMT) models largely depends on the vocabulary used at training; small vocabularies can lead to out-of-vocabulary problems -- large ones, to memory issues. Subword (SW) tokenization has been…

Computation and Language · Computer Science 2023-03-02 J. Pourmostafa Roshan Sharami , D. Shterionov , P. Spronck

Tokenization significantly influences language models(LMs)' performance. This paper traces the evolution of tokenizers from word-level to subword-level, analyzing how they balance tokens and types to enhance model adaptability while…

Computation and Language · Computer Science 2024-03-04 Jinbiao Yang

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Machine Learning · Computer Science 2024-04-09 Bowen Pan , Yikang Shen , Haokun Liu , Mayank Mishra , Gaoyuan Zhang , Aude Oliva , Colin Raffel , Rameswar Panda

While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current…

Computation and Language · Computer Science 2024-08-01 Anqi Zhang , Chaofeng Wu

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of…

Sound · Computer Science 2024-01-17 Feiyu Shen , Yiwei Guo , Chenpeng Du , Xie Chen , Kai Yu

We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs). We propose two novel approaches: (1) a similarity-based…

Computation and Language · Computer Science 2025-03-20 Milad Fotouhi , Mohammad Taha Bahadori , Oluwaseyi Feyisetan , Payman Arabshahi , David Heckerman

Large language model (LLM) tokenizers act as structured compressors: by mapping text to discrete token sequences, they determine token count (and thus compute and context usage) and the statistical structure seen by downstream models.…

Information Theory · Computer Science 2026-01-15 Mete Erdogan , Abhiram Gorle , Shubham Chandak , Mert Pilanci , Tsachy Weissman

Tokenization is a crucial step in NLP, especially with the rise of large language models (LLMs), impacting downstream performance, computational cost, and efficiency. Existing LLMs rely on the classical Byte-pair Encoding (BPE) algorithm…

Computation and Language · Computer Science 2025-11-10 Maharaj Brahma , N J Karthika , Atul Singh , Devaraj Adiga , Smruti Bhate , Ganesh Ramakrishnan , Rohit Saluja , Maunendra Sankar Desarkar

One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for…

Computation and Language · Computer Science 2023-04-21 Verena Blaschke , Hinrich Schütze , Barbara Plank

The performance of large language models (LLMs) is significantly affected by the quality and composition of their pre-training data, which is inherently diverse, spanning various languages, sources, and topics. Effectively integrating these…

Computation and Language · Computer Science 2025-08-11 Jiahui Peng , Xinlin Zhuang , Jiantao Qiu , Ren Ma , Jing Yu , He Zhu , Conghui He

This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units. We view the subword segmentation of output sentences as a latent variable that should be marginalized out…

Computation and Language · Computer Science 2020-08-04 Xuanli He , Gholamreza Haffari , Mohammad Norouzi

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

Computation and Language · Computer Science 2023-03-14 Anh Nguyen , Nikos Karampatziakis , Weizhu Chen

Data mixing decides how to combine different sources or types of data and is a consequential problem throughout language model training. In pretraining, data composition is a key determinant of model quality; in continual learning and…

Computation and Language · Computer Science 2026-05-18 Michael Y. Hu , Apurva Gandhi , Kyunghyun Cho , Tal Linzen , Pratyusha Sharma

Byte pair encoding (BPE) emerges as an effective tokenization method for tackling the out-of-vocabulary (OOV) challenge in various natural language and speech processing tasks. Recent research highlights the dependency of BPE subword…

Computation and Language · Computer Science 2024-01-30 Ahnaf Mozib Samin

Language models often pre-train on large unsupervised text corpora, then fine-tune on additional task-specific data. However, typical fine-tuning schemes do not prioritize the examples that they tune on. We show that, if you can prioritize…

Computation and Language · Computer Science 2023-05-12 Ian Osband , Seyed Mohammad Asghari , Benjamin Van Roy , Nat McAleese , John Aslanides , Geoffrey Irving

Recent dynamic tokenisation methods operate directly on bytes and pool their latent representations into patches. This bears similarities to computational models of word segmentation that determine lexical boundaries using spikes in an…

Computation and Language · Computer Science 2025-06-24 Zébulon Goriely , Suchir Salhan , Pietro Lesci , Julius Cheng , Paula Buttery

What are the units of text that we want to model? From bytes to multi-word expressions, text can be analyzed and generated at many granularities. Until recently, most natural language processing (NLP) models operated over words, treating…

Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream generalization under realistic compute and data budget…

Computation and Language · Computer Science 2026-04-21 Zhuo Chen , Yuxuan Miao , Supryadi , Deyi Xiong

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and…

‹ Prev 1 3 4 5 6 7 10 Next ›