paper-with-me

홈 › Papers

Scaling LLM Pre-training with Vocabulary Curriculum

2025-02-25 · Fangyuan Yu

Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an approach that improves pretraining efficiency with log-linear scaling gains relative to vocabulary size. Our method alternates between entropy-guided vocabulary expansion and model optimization, enabling models to learn transferable representations across diverse tokenization granularities. This approach naturally gives rise to an optimal computation allocation pattern: longer tokens capture predictable content, while shorter tokens focus on more complex, harder-to-predict contexts. Experiments on small-scale GPT models demonstrate improved scaling efficiency, reinforcing the effectiveness of dynamic tokenization. We release our code to support further research and plan to extend our experiments to larger models and diverse domains.

📄 PDF Abstract BibTeX arXiv:2502.17910

Code (0)

등록된 구현이 없습니다.

Tasks

Model Optimization

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution

2026-04-03 · Jacob Dineen, Aswin RRV, Zhikun Xu, Ben Zhou arxiv

Co-evolutionary self-play, where one language model generates problems and another solves them, promises curriculum learning without human supervision. The promise breaks down early in practice. The proposer converges to…

Mathematical Reasoning

Towards Data-Efficient Language Models: A Child-Inspired Approach to Language Learning

2025-03-06 · Mohammad Amin Ghanizadeh, Mohammad Javad Dousti

In this work, we explain our approach employed in the BabyLM Challenge, which uses various methods of training language models (LMs) with significantly less data compared to traditional large language models (LLMs) and a…

Language Acquisition

Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

2024-07-18 · Chaofan Tao, Qian Liu, Longxu Dou, Niklas Muennighoff 외

Research on scaling large language models (LLMs) has primarily focused on model parameters and training data size, overlooking the role of vocabulary size. We investigate how vocabulary size impacts LLM scaling laws by t…

ARC

Curriculum Q-Learning for Visual Vocabulary Acquisition

2017-11-29 · Ahmed H. Zaidi, Russell Moore, Ted Briscoe

The structure of curriculum plays a vital role in our learning process, both as children and adults. Presenting material in ascending order of difficulty that also exploits prior knowledge can have a significant impact o…

Q-LearningReinforcement Learning

CLIMB: Curriculum Learning for Infant-inspired Model Building

2023-11-15 · Richard Diehl Martinez, Zebulon Goriely, Hope McGovern, Christopher Davis 외

We describe our team's contribution to the STRICT-SMALL track of the BabyLM Challenge. The challenge requires training a language model from scratch using only a relatively small training dataset of ten million words. We…

Language ModelingLanguage ModellingMasked Language Modelingmodel