English
Related papers

Related papers: Training Language Models with homotokens Leads to …

200 papers

Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks. However, it modifies all the language model parameters and therefore necessitates storing a full copy for each task. In this paper, we…

Computation and Language · Computer Science 2021-01-05 Xiang Lisa Li , Percy Liang

Large language models are trained with tokenizers, and the resulting token distribution is highly imbalanced: a few words dominate the stream while most occur rarely. Recent practice favors ever-larger vocabularies, but it is unclear where…

Computation and Language · Computer Science 2025-12-01 Woojin Chung , Jeonghoon Kim

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even…

Machine Learning · Computer Science 2018-01-31 Łukasz Kaiser , Samy Bengio

This study introduces a novel knowledge enhanced tokenisation mechanism, K-Tokeniser, for clinical text processing. Technically, at initialisation stage, K-Tokeniser populates global representations of tokens based on semantic types of…

Computation and Language · Computer Science 2024-06-21 Abul Hasan , Jinge Wu , Quang Ngoc Nguyen , Salomé Andres , Imane Guellil , Huayu Zhang , Arlene Casey , Beatrice Alex , Bruce Guthrie , Honghan Wu

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2024-05-01 Fabian Gloeckle , Badr Youbi Idrissi , Baptiste Rozière , David Lopez-Paz , Gabriel Synnaeve

Character-level language models obviate the need for separately trained tokenizers, but efficiency suffers from longer sequence lengths. Learning to combine character representations into tokens has made training these models more…

Computation and Language · Computer Science 2023-11-16 William Fleshman , Benjamin Van Durme

Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system…

Computation and Language · Computer Science 2023-02-16 Chenglei Si , Zhengyan Zhang , Yingfa Chen , Fanchao Qi , Xiaozhi Wang , Zhiyuan Liu , Yasheng Wang , Qun Liu , Maosong Sun

We propose ContextLM, a framework that implicitly learns multi-token prediction by augmenting standard pretraining with an intrinsic next-context prediction objective. ContextLM builds a language model on top of context embeddings that span…

Computation and Language · Computer Science 2026-02-12 Beiya Dai , Yuliang Liu , Daozheng Xue , Yunchong Song , Qipeng Guo , Kai Chen , Xinbing Wang , Bowen Zhou , Zhouhan Lin

How do language models learn to make predictions during pre-training? To study this, we extract learning curves from five autoregressive English language model pre-training runs, for 1M unseen tokens in context. We observe that the language…

Computation and Language · Computer Science 2024-08-01 Tyler A. Chang , Zhuowen Tu , Benjamin K. Bergen

Recent research suggests that the feed-forward module within Transformers can be viewed as a collection of key-value memories, where the keys learn to capture specific patterns from the input based on the training examples. The values then…

Computation and Language · Computer Science 2023-10-25 Sunit Bhattacharya , Ondrej Bojar

When using an LLM to process text outside the training domain(s), an often overlooked factor is vocabulary mismatch, where the general-domain tokenizer fails to capture frequent domain-specific terms, leading to higher token fertility and…

Computation and Language · Computer Science 2025-10-01 Christian Herold , Michael Kozielski , Nicholas Santavas , Yannick Versley , Shahram Khadivi

Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also…

Computation and Language · Computer Science 2025-06-05 Chong Li , Jiajun Zhang , Chengqing Zong

Static subword tokenization algorithms have been an essential component of recent works on language modeling. However, their static nature results in important flaws that degrade the models' downstream performance and robustness. In this…

Computation and Language · Computer Science 2022-12-15 Nathan Godey , Roman Castagné , Éric de la Clergerie , Benoît Sagot

Multilingual pre-trained models are known to suffer from the curse of multilinguality, which causes per-language performance to drop as they cover more languages. We address this issue by introducing language-specific modules, which allows…

Computation and Language · Computer Science 2022-05-13 Jonas Pfeiffer , Naman Goyal , Xi Victoria Lin , Xian Li , James Cross , Sebastian Riedel , Mikel Artetxe

Commonly-used transformer language models depend on a tokenization schema which sets an unchangeable subword vocabulary prior to pre-training, destined to be applied to all downstream tasks regardless of domain shift, novel word formations,…

Computation and Language · Computer Science 2021-08-03 Yuval Pinter , Amanda Stent , Mark Dredze , Jacob Eisenstein

Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies…

Software Engineering · Computer Science 2021-01-01 Fang Liu , Ge Li , Yunfei Zhao , Zhi Jin

Pre-trained language models for code (PLMCs) have gained attention in recent research. These models are pre-trained on large-scale datasets using multi-modal objectives. However, fine-tuning them requires extensive supervision and is…

Computation and Language · Computer Science 2023-05-11 Hung Quoc To , Nghi D. Q. Bui , Jin Guo , Tien N. Nguyen

Sequence-to-sequence (seq2seq) models have been widely used for natural language processing, computer vision, and other deep learning tasks. We find that seq2seq models trained with early-stopping suffer from issues at the token level. In…

Computation and Language · Computer Science 2023-06-23 Guangsheng Bao , Zhiyang Teng , Yue Zhang

Understanding architectural differences in language models is challenging, especially at academic-scale pretraining (e.g., 1.3B parameters, 100B tokens), where results are often dominated by noise and randomness. To overcome this, we…

Computation and Language · Computer Science 2025-12-22 Zeyuan Allen-Zhu

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Machine Learning · Computer Science 2025-05-20 Yuchang Sun , Yanxi Chen , Yaliang Li , Bolin Ding
‹ Prev 1 3 4 5 6 7 10 Next ›