Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

• URL: http://arxiv.org/abs/2507.07955v2
• Date: Tue, 15 Jul 2025 09:06:11 GMT
• Title: Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
• Authors: Sukjun Hwang, Brandon Wang, Albert Gu,
• Abstract summary: We introduce techniques that enable a dynamic chunking mechanism which automatically learns content- and context- dependent segmentation strategies.<n> incorporating this into an explicit hierarchical network (H-Net) allows replacing the (implicitly hierarchical) tokenization-LM-detokenization pipeline with a single model learned fully end-to-end.<n>Iterating the hierarchy to multiple stages further increases its performance by modeling multiple levels of abstraction.<n>H-Nets pretrained on English show significantly increased character-level robustness, and qualitatively learn meaningful data-dependent chunking strategies without anys or explicit supervision.
• Score: 17.277753030570263
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Major progress on language models (LMs) in recent years has largely resulted from moving away from specialized models designed for specific tasks, to general models based on powerful architectures (e.g. the Transformer) that learn everything from raw data. Despite this trend, pre-processing steps such as tokenization remain a barrier to true end-to-end foundation models. We introduce a collection of new techniques that enable a dynamic chunking mechanism which automatically learns content- and context- dependent segmentation strategies learned jointly with the rest of the model. Incorporating this into an explicit hierarchical network (H-Net) allows replacing the (implicitly hierarchical) tokenization-LM-detokenization pipeline with a single model learned fully end-to-end. When compute- and data- matched, an H-Net with one stage of hierarchy operating at the byte level outperforms a strong Transformer language model operating over BPE tokens. Iterating the hierarchy to multiple stages further increases its performance by modeling multiple levels of abstraction, demonstrating significantly better scaling with data and matching the token-based Transformer of twice its size. H-Nets pretrained on English show significantly increased character-level robustness, and qualitatively learn meaningful data-dependent chunking strategies without any heuristics or explicit supervision. Finally, the H-Net's improvement over tokenized pipelines is further increased in languages and modalities with weaker tokenization heuristics, such as Chinese and code, or DNA sequences (nearly 4x improvement in data efficiency over baselines), showing the potential of true end-to-end models that learn and scale better from unprocessed data.

Related papers

• ORIGAMI: A generative transformer architecture for predictions from semi-structured data [3.5639148953570836]
  ORIGAMI is a transformer-based architecture that processes nested key/value pairs.<n>By reformulating classification as next-token prediction, ORIGAMI naturally handles both single-label and multi-label tasks.
  arXiv  Detail & Related papers  (2024-12-23T07:21:17Z)
• Byte Latent Transformer: Patches Scale Better Than Tokens [101.10994909832063]
  Byte Latent Transformer (BLT) encodes bytes into dynamically sized patches, which serve as the primary units of computation.<n>For fixed inference costs, BLT shows significantly better scaling than tokenization-based models, by simultaneously growing both patch and model size.
  arXiv  Detail & Related papers  (2024-12-13T05:33:32Z)
• How to Make LLMs Strong Node Classifiers? [70.14063765424012]
  Language Models (LMs) are challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs)<n>We propose a novel approach that empowers off-the-shelf LMs to achieve performance comparable to state-of-the-art (SOTA) GNNs on node classification tasks.
  arXiv  Detail & Related papers  (2024-10-03T08:27:54Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Transformer Architecture for NetsDB [0.0]
  We create an end-to-end implementation of a transformer for deep learning model serving in NetsDB. We load out weights from our model for distributed processing, deployment, and efficient inferencing.
  arXiv  Detail & Related papers  (2024-05-08T04:38:36Z)
• FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction [49.510163437116645]
  Click-through rate (CTR) prediction plays as a core function module in personalized online services. Traditional ID-based models for CTR prediction take as inputs the one-hot encoded ID features of tabular modality. Pretrained Language Models(PLMs) has given rise to another paradigm, which takes as inputs the sentences of textual modality. We propose to conduct Fine-grained feature-level ALignment between ID-based Models and Pretrained Language Models(FLIP) for CTR prediction.
  arXiv  Detail & Related papers  (2023-10-30T11:25:03Z)
• Autoregressive Structured Prediction with Language Models [73.11519625765301]
  We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
  arXiv  Detail & Related papers  (2022-10-26T13:27:26Z)
• Pre-Training a Graph Recurrent Network for Language Representation [34.4554387894105]
  We consider a graph recurrent network for language model pre-training, which builds a graph structure for each sequence with local token-level communications. We find that our model can generate more diverse outputs with less contextualized feature redundancy than existing attention-based models.
  arXiv  Detail & Related papers  (2022-09-08T14:12:15Z)
• GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures [57.46093180685175]
  We demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. We add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales.
  arXiv  Detail & Related papers  (2021-06-10T15:41:53Z)
• Revisiting Simple Neural Probabilistic Language Models [27.957834093475686]
  This paper revisits the neural probabilistic language model (NPLM) ofcitetBengio2003ANP. When scaled up to modern hardware, this model performs much better than expected on word-level language model benchmarks. Inspired by this result, we modify the Transformer by replacing its first self-attention layer with the NPLM's local concatenation layer.
  arXiv  Detail & Related papers  (2021-04-08T02:18:47Z)
• SDA: Improving Text Generation with Self Data Augmentation [88.24594090105899]
  We propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, our method is more general and could be easily adapted to any MLE-based training procedure.
  arXiv  Detail & Related papers  (2021-01-02T01:15:57Z)
• Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
  We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking. We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
  arXiv  Detail & Related papers  (2020-10-24T11:55:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.