English
Related papers

Related papers: TREX: Tokenizer Regression for Optimal Data Mixtur…

200 papers

Pretrained language models (LLMs) are often constrained by their fixed tokenization schemes, leading to inefficiencies and performance limitations, particularly for multilingual or specialized applications. This tokenizer lock-in presents…

Computation and Language · Computer Science 2025-05-16 Shaurya Sharthak , Vinayak Pahalwan , Adithya Kamath , Adarsh Shirawalmath

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…

Machine Learning · Computer Science 2026-05-14 Paul Jeha , Anastasiia Sedova , Louis Béthune , Skyler Seto , Jes Frellsen , Pierre Ablin , Natalie Schluter

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Computation and Language · Computer Science 2026-05-14 Chong Li , Yingzhuo Deng , Wen Yang , Jiajun Zhang , Chengqing Zong

Data selection is a key component of efficient instruction tuning for large language models, as recent work has shown that data quality often matters more than data quantity. Accordingly, prior studies have introduced various…

Machine Learning · Computer Science 2026-05-12 Jingze Song , Zihao Chen , Wenqing Chen , Zibin Zheng

Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic architecture, enabling effective task decoupling. However,…

Machine Learning · Computer Science 2025-05-28 Rongyu Zhang , Yijiang Liu , Huanrui Yang , Shenli Zheng , Dan Wang , Yuan Du , Li Du , Shanghang Zhang

When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong…

Machine Learning · Computer Science 2025-06-03 Nicholas E. Corrado , Julian Katz-Samuels , Adithya Devraj , Hyokun Yun , Chao Zhang , Yi Xu , Yi Pan , Bing Yin , Trishul Chilimbi

Scaling laws enable the optimal selection of data amount and language model size, yet the impact of the data unit, the token, on this relationship remains underexplored. In this work, we systematically investigate how the information…

Computation and Language · Computer Science 2026-05-27 Tomasz Limisiewicz , Artidoro Pagnoni , Srini Iyer , Mike Lewis , Sachin Mehta , Alisa Liu , Margaret Li , Gargi Ghosh , Luke Zettlemoyer

Although large language models (LLMs) have demonstrated their strong intelligence ability, the high demand for computation and storage hinders their practical application. To this end, many model compression techniques are proposed to…

Computation and Language · Computer Science 2024-11-01 Ge Yang , Changyi He , Jinyang Guo , Jianyu Wu , Yifu Ding , Aishan Liu , Haotong Qin , Pengliang Ji , Xianglong Liu

As language models increase in size by the day, methods for efficient inference are critical to leveraging their capabilities for various applications. Prior work has investigated techniques like model pruning, knowledge distillation, and…

Machine Learning · Computer Science 2023-08-25 Yushan Su , Vishvak Murahari , Karthik Narasimhan , Kai Li

Using pre-trained large language models (LLMs) as a backbone for time series prediction has recently attracted growing research interest. Existing approaches typically split time series into patches, map them to the token space of LLMs via…

Machine Learning · Computer Science 2026-03-09 Xinyu Zhang , Shanshan Feng , Xutao Li , Kenghong Lin , Fan Li , Pengfei Jia

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading…

Machine Learning · Computer Science 2025-02-25 Wei Huang , Yue Liao , Jianhui Liu , Ruifei He , Haoru Tan , Shiming Zhang , Hongsheng Li , Si Liu , Xiaojuan Qi

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

Software Engineering · Computer Science 2026-02-10 Viacheslav Siniaev , Iaroslav Chelombitko , Aleksey Komissarov

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

Computation and Language · Computer Science 2025-02-24 Weilan Wang , Yu Mao , Dongdong Tang , Hongchao Du , Nan Guan , Chun Jason Xue

Quantization is an effective technique for reducing the storage footprint and computational costs of Large Language Models (LLMs), but it often results in performance degradation. Existing post-training quantization methods typically use…

Computation and Language · Computer Science 2026-01-27 Everlyn Asiko Chimoto , Mostafa Elhoushi , Bruce A. Bassett

The pretraining data of today's strongest language models is opaque; in particular, little is known about the proportions of various domains or languages represented. In this work, we tackle a task which we call data mixture inference,…

Computation and Language · Computer Science 2024-12-03 Jonathan Hayase , Alisa Liu , Yejin Choi , Sewoong Oh , Noah A. Smith

Large language models (LLMs) have brought a great breakthrough to the natural language processing (NLP) community, while leading the challenge of handling concurrent customer queries due to their high throughput demands. Data multiplexing…

Computation and Language · Computer Science 2024-10-08 Yige Xu , Xu Guo , Zhiwei Zeng , Chunyan Miao

Adapting language models to new data distributions by simple finetuning is challenging. This is due to the rigidity of their subword tokenizers, which typically remain unchanged during adaptation. This inflexibility often leads to…

Computation and Language · Computer Science 2026-05-14 Abraham Toluwase Owodunni , Orevaoghene Ahia , Sachin Kumar

Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perplexity. We propose Continuous Concept Mixing (CoCoMix), a…

Machine Learning · Computer Science 2025-02-13 Jihoon Tack , Jack Lanchantin , Jane Yu , Andrew Cohen , Ilia Kulikov , Janice Lan , Shibo Hao , Yuandong Tian , Jason Weston , Xian Li

Recent research has shown that pruning large-scale language models for inference is an effective approach to improving model efficiency, significantly reducing model weights with minimal impact on performance. Interestingly, pruning can…

Computation and Language · Computer Science 2025-02-19 Yiran Luo , Het Patel , Yu Fu , Dawon Ahn , Jia Chen , Yue Dong , Evangelos E. Papalexakis

Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation. This work addresses this limitation through a synthetic data…

Computation and Language · Computer Science 2025-09-25 Sen Yang , Yu Bao , Yu Lu , Jiajun Chen , Shujian Huang , Shanbo Cheng