English
Related papers

Related papers: Lossless Vocabulary Reduction for Auto-Regressive …

200 papers

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

Computation and Language · Computer Science 2016-10-14 Yunchuan Chen , Lili Mou , Yan Xu , Ge Li , Zhi Jin

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

Computation and Language · Computer Science 2024-08-28 Shannon Zejiang Shen , Hunter Lang , Bailin Wang , Yoon Kim , David Sontag

Music generation schemes using language modeling rely on a vocabulary of audio tokens, generally provided as codes in a discrete latent space learnt by an auto-encoder. Multi-stage quantizers are often employed to produce these tokens,…

Sound · Computer Science 2024-06-11 Jean-Marie Lemercier , Simon Rouard , Jade Copet , Yossi Adi , Alexandre Défossez

Transformers are responsible for the vast majority of recent advances in natural language processing. The majority of practical natural language processing applications of these models are typically enabled through transfer learning. This…

Computation and Language · Computer Science 2024-02-02 Vladislav Mosin , Igor Samenko , Alexey Tikhonov , Borislav Kozlovskii , Ivan P. Yamshchikov

Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve…

Computation and Language · Computer Science 2019-01-08 Yunsu Kim , Jiahui Geng , Hermann Ney

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token…

Computation and Language · Computer Science 2020-10-22 Huaao Zhang , Shigui Qiu , Xiangyu Duan , Min Zhang

This paper proposes a method to optimize tokenization for the performance improvement of already trained downstream models. Our method generates tokenization results attaining lower loss values of a given downstream model on the training…

Computation and Language · Computer Science 2023-04-24 Tatsuya Hiraoka , Tomoya Iwakura

Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks trained on the simple task of next-token prediction. In…

Machine Learning · Computer Science 2024-07-31 Eran Malach

Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…

Computation and Language · Computer Science 2025-08-11 Alistair Dombrowski , Beatrix Engelhardt , Dimitri Fairbrother , Henry Evidail

Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a…

Computation and Language · Computer Science 2019-09-05 Marjan Ghazvininejad , Omer Levy , Yinhan Liu , Luke Zettlemoyer

Modern language models operate on subword-tokenized text in order to make a trade-off between model size, inference speed, and vocabulary coverage. A side effect of this is that, during inference, models are evaluated by measuring the…

Computation and Language · Computer Science 2025-10-24 David Pohl , Marco Cognetta , Junyoung Lee , Naoaki Okazaki

Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…

Computation and Language · Computer Science 2025-05-29 Haoming Xu , Ningyuan Zhao , Liming Yang , Sendong Zhao , Shumin Deng , Mengru Wang , Bryan Hooi , Nay Oo , Huajun Chen , Ningyu Zhang

Large language models (LLMs) trained with canonical tokenization exhibit surprising robustness to non-canonical inputs such as character-level tokenization, yet the mechanisms underlying this robustness remain unclear. We study this…

Computation and Language · Computer Science 2026-03-12 Zhipeng Yang , Shu Yang , Lijie Hu , Di Wang

Tokenization is a necessary component within the current architecture of many language mod-els, including the transformer-based large language models (LLMs) of Generative AI, yet its impact on the model's cognition is often overlooked. We…

There is an intuitive analogy of an organic chemist's understanding of a compound and a language speaker's understanding of a word. Consequently, it is possible to introduce the basic concepts and analyze potential impacts of linguistic…

Machine Learning · Computer Science 2017-11-16 Philippe Schwaller , Theophile Gaudin , David Lanyi , Costas Bekas , Teodoro Laino

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword…

Computation and Language · Computer Science 2026-05-15 Théo Gigant , Bowen Peng , Jeffrey Quesnelle

Large Language Models (LLMs) rely on generating extensive intermediate reasoning units (e.g., tokens, sentences) to enhance final answer quality across a wide range of complex tasks. While this approach has proven effective, it inevitably…

Computation and Language · Computer Science 2025-06-05 Joonwon Jang , Jaehee Kim , Wonbin Kweon , Seonghyeon Lee , Hwanjo Yu

Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…

Computation and Language · Computer Science 2024-04-09 Yilin Wang , Xinyi Hu , Matthew R. Gormley

We propose V2Flow, a novel tokenizer that produces discrete visual tokens capable of high-fidelity reconstruction, while ensuring structural and latent distribution alignment with the vocabulary space of large language models (LLMs).…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Guiwei Zhang , Tianyu Zhang , Mohan Zhou , Yalong Bai , Biye Li

Transformer language models can generate strikingly natural text by modeling language as a sequence of tokens, but by relying primarily on surface-level co-occurrence statistics they fail to form globally consistent latent representations…

Computation and Language · Computer Science 2026-01-14 Nasim Borazjanizadeh , James McClelland
‹ Prev 1 3 4 5 6 7 10 Next ›