English
Related papers

Related papers: Cross-Tokenizer Likelihood Scoring Algorithms for …

200 papers

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

Computation and Language · Computer Science 2025-10-27 Benjamin Minixhofer , Ivan Vulić , Edoardo Maria Ponti

Cross-tokenizer knowledge distillation allows a student model to learn from teachers with incompatible vocabularies. Prior work operates on hidden states or logits; the latter is preferred as a drop-in replacement requiring no auxiliary…

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing…

Computation and Language · Computer Science 2025-04-15 Buu Phan , Brandon Amos , Itai Gat , Marton Havasi , Matthew Muckley , Karen Ullrich

In the current work, we connect token-level uncertainty in causal language modeling to two types of training objectives: 1) masked maximum likelihood (MLE), 2) self-distillation. We show that masked MLE is effective in reducing epistemic…

Computation and Language · Computer Science 2025-03-24 Tingkai Liu , Ari S. Benjamin , Anthony M. Zador

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

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Computation and Language · Computer Science 2026-03-16 Ryan Brown , Chris Russell

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

Byte Language Models (BLMs) have emerged as a promising direction for scaling language models beyond tokenization. However, existing BLMs typically require training from scratch on trillions of bytes, making them prohibitively expensive. In…

Computation and Language · Computer Science 2026-02-03 Zishuo Bao , Jiaqi Leng , Junxiong Wang , Bowen Peng , Yucheng Lu

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists: long tokens, rich…

Computation and Language · Computer Science 2024-11-11 Haoran Lian , Yizhe Xiong , Zijia Lin , Jianwei Niu , Shasha Mo , Hui Chen , Peng Liu , Guiguang Ding

Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be large in this…

Computation and Language · Computer Science 2022-09-14 Kunbo Ding , Weijie Liu , Yuejian Fang , Zhe Zhao , Qi Ju , Xuefeng Yang

Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters for competitive performance. While existing distillation methods for dLLMs reduce inference…

Computation and Language · Computer Science 2026-04-30 Gongbo Zhang , Wen Wang , Ye Tian , Li Yuan

Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has…

Computation and Language · Computer Science 2024-10-08 Craig W. Schmidt , Varshini Reddy , Haoran Zhang , Alec Alameddine , Omri Uzan , Yuval Pinter , Chris Tanner

Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…

Machine Learning · Computer Science 2025-07-25 Anshumann , Mohd Abbas Zaidi , Akhil Kedia , Jinwoo Ahn , Taehwak Kwon , Kangwook Lee , Haejun Lee , Joohyung Lee

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

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

We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair…

Machine Learning · Statistics 2017-07-06 Bart van Merriënboer , Amartya Sanyal , Hugo Larochelle , Yoshua Bengio

State-of-the-art language models are autoregressive and operate on subword units known as tokens. Specifically, one must encode the conditioning string into a list of tokens before passing to the language models for next-token prediction.…

Computation and Language · Computer Science 2024-07-09 Buu Phan , Marton Havasi , Matthew Muckley , Karen Ullrich

Cross-tokenizer distillation (CTD), the transfer of knowledge from a teacher to a student language model when the two use different tokenizers, remains a largely unsolved problem. Existing approaches rely on heuristic strategies to align…

Computation and Language · Computer Science 2026-04-14 Avyav Kumar Singh , Yen-Chen Wu , Alexandru Cioba , Alberto Bernacchia , Davide Buffelli

Tokenization is used almost universally by modern language models, enabling efficient text representation using multi-byte or multi-character tokens. However, prior work has shown that tokenization can introduce distortion into the model's…

Computation and Language · Computer Science 2026-05-08 Jonathan Hayase , Alisa Liu , Noah A. Smith , Sewoong Oh

With the rapid progress of speech language models (SLMs), discrete speech tokens have emerged as a core interface between speech and text, enabling unified modeling across modalities. Recent speech tokenization approaches aim to isolate…

Computation and Language · Computer Science 2025-06-23 Daejin Jo , Jeeyoung Yun , Byungseok Roh , Sungwoong Kim
‹ Prev 1 2 3 10 Next ›