← Back to all news
arXiv Machine Learning By Shulei Wang

Learning Representations through Token Prediction: Geometry, Approximation, and Downstream Guarantees

Read the original on arXiv Machine Learning →

The paper investigates why token prediction, a common pre‑training objective for language models, yields useful representations. It introduces a statistical framework linking token prediction accuracy to the geometry of token embeddings, showing that accurate predictions organize embeddings according to Hellinger distances between context distributions. The authors also propose a self‑consistency principle that refines contextual representations through repeated application of a shared block, and provide downstream guarantees for token generation, community recovery, and linear classification.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 28

Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation

The paper examines how new vocabulary tokens are added to language models for generative recommendation tasks. It shows that the common practice of initializing these tokens as the mean of existing embeddings collapses them into a degenerate subspace, hindering fine‑tuning. The authors propose Grounded Token Initialization (GTI), which places new tokens at semantically meaningful positions in the pretrained embedding space using linguistic supervision, and demonstrate that GTI outperforms mean initialization and other adaptation methods across several benchmarks.

By Daiwei Chen, Zhoutong Fu, Chengming Jiang, Haichao Zhang, Ran Zhou, Tan Wang, Chunnan Yao, Guoyao Li, Rui Cai, Yihan Cao, Ruijie Jiang, Fedor Borisyuk, Jianqiang Shen, Jingwei Wu, Ramya Korlakai Vinayak
llmsragfine-tuningbenchmarks
More like this →
arXiv Computation and Language
5d ago

No Single Tokenizer Feature Reliably Predicts Downstream Language Model Performance

The paper investigates whether intrinsic tokenizer features can predict the performance of downstream language models. By training about 200 models across nine languages and evaluating numerous tokenizer metrics, the authors find that none of the existing metrics consistently forecasts model performance across different families, tasks, and languages. They propose a new linguistically grounded metric that captures aspects of tokenizer quality missed by prior measures, though its predictive power may still vary.

By Antonio Lopardo, Luis Frentzen Salim, Shikhar Srivastava, Kevin Jiang, Mridul Sharma, Catherine Arnett
llmsnlpbenchmarks
More like this →
arXiv AI
Sep 28

Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning

The paper introduces TokenAdapt, a model‑agnostic tokenizer transplantation method that uses a hybrid heuristic to initialize new token embeddings, and a novel pre‑tokenization learning approach for multi‑word Supertokens to improve compression. TokenAdapt combines local subword decomposition and global semantic similarity to preserve semantics while reducing retraining needs. Empirical results show that TokenAdapt outperforms existing baselines such as Transtokenizer and ReTok, achieving lower perplexity ratios and significant compression gains.

By Shaurya Sharthak, Vinayak Pahalwan, Adithya Kamath, Adarsh Shirawalmath
llmsragnlpfine-tuning
More like this →