English
Related papers

Related papers: On the Effect of Token Merging on Pre-trained Mode…

200 papers

Since traditional tokenizers are isolated from a downstream task and model, they cannot output an appropriate tokenization depending on the task and model, although recent studies imply that the appropriate tokenization improves the…

Computation and Language · Computer Science 2021-05-27 Tatsuya Hiraoka , Sho Takase , Kei Uchiumi , Atsushi Keyaki , Naoaki Okazaki

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

Computation and Language · Computer Science 2018-11-15 Marek Rei , Anders Søgaard

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Tianyu Fu , Tengxuan Liu , Qinghao Han , Guohao Dai , Shengen Yan , Huazhong Yang , Xuefei Ning , Yu Wang

Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs). Despite the importance of tokenization, its role in LM performance and behavior is poorly understood due to the challenge of…

Computation and Language · Computer Science 2025-12-25 Gül Sena Altıntaş , Malikeh Ehghaghi , Brian Lester , Fengyuan Liu , Wanru Zhao , Marco Ciccone , Colin Raffel

Choosing an appropriate tokenization scheme is often a bottleneck in low-resource cross-lingual transfer. To understand the downstream implications of text representation choices, we perform a comparative analysis on language models having…

Computation and Language · Computer Science 2023-10-13 Md Mushfiqur Rahman , Fardin Ahsan Sakib , Fahim Faisal , Antonios Anastasopoulos

Subword tokenization requires balancing computational efficiency and vocabulary coverage, which often leads to suboptimal performance on languages and scripts not prioritized during training. We propose to augment pretrained language models…

Computation and Language · Computer Science 2025-08-12 Jonas F. Lotz , Hendra Setiawan , Stephan Peitz , Yova Kementchedjhieva

Large language models (LLMs) excel in many natural language tasks, yet they struggle with complex mathemat-ical problem-solving, particularly in symbolic reasoning and maintaining consistent output. This study evalu-ates 10 LLMs with 7 to 8…

Machine Learning · Computer Science 2025-01-29 Evgenii Evstafev

Vector quantization is a technique in machine learning that discretizes continuous representations into a set of discrete vectors. It is widely employed in tokenizing data representations for large language models, diffusion models, and…

Machine Learning · Computer Science 2026-03-19 Wenhao Zhao , Qiran Zou , Rushi Shah , Yudi Wu , Zhouhan Lin , Dianbo Liu

Large language models (LLMs) have shown exceptional performance in code generation and understanding tasks, yet their high computational costs hinder broader adoption. One important factor is the inherent verbosity of programming languages,…

Software Engineering · Computer Science 2025-12-10 Zhensu Sun , Chengran Yang , Xiaoning Du , Zhou Yang , Li Li , David Lo

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Computation and Language · Computer Science 2025-08-22 Dong Liu , Yanxuan Yu

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Junzhu Mao , Yang Shen , Jinyang Guo , Yazhou Yao , Xiansheng Hua

We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in…

Computation and Language · Computer Science 2023-10-03 Bar Iluz , Tomasz Limisiewicz , Gabriel Stanovsky , David Mareček

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

The number of tokens it takes to encode parallel text in different languages is known to vary. These disparities are called token premiums. Having high token premiums leads to less throughput during training and increases costs at…

Computation and Language · Computer Science 2025-10-28 Catherine Arnett , Tyler A. Chang , Stella Biderman , Benjamin K. Bergen

Subword tokenizers trained on multilingual corpora naturally produce overlapping tokens across languages. Does token overlap facilitate cross-lingual transfer or instead introduce interference between languages? Prior work offers mixed…

Computation and Language · Computer Science 2025-09-26 Julie Kallini , Dan Jurafsky , Christopher Potts , Martijn Bartelds

Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the…

Computation and Language · Computer Science 2025-06-04 Pietro Lesci , Clara Meister , Thomas Hofmann , Andreas Vlachos , Tiago Pimentel

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

Past research has examined how well these models grasp code syntax, yet their understanding of code semantics still needs to be explored. We extensively analyze seven code models to investigate how code models represent code syntax and…

Software Engineering · Computer Science 2024-04-18 Wei Ma , Shangqing Liu , Mengjie Zhao , Xiaofei Xie , Wenhan Wang , Qiang Hu , Jie Zhang , Yang Liu

Large Language Models (LLMs) incur significant computational and memory costs when processing long prompts, as full self-attention scales quadratically with input length. Token compression aims to address this challenge by reducing the…

Computation and Language · Computer Science 2026-04-23 Zihao Xu , John Harvill , Ziwei Fan , Yizhou Sun , Hao Ding , Hao Wang

The lack of transparency about code datasets used to train large language models (LLMs) makes it difficult to detect, evaluate, and mitigate data leakage. We present a perturbation-based method to quantify memorization advantage in code…