Making Language Model a Hierarchical Classifier

• URL: http://arxiv.org/abs/2507.12930v2
• Date: Sun, 28 Sep 2025 14:57:03 GMT
• Title: Making Language Model a Hierarchical Classifier
• Abstract summary: Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers decoding texts simultaneously.<n>This study suggests the possibility of a generalized hierarchical reasoner, pretraining from scratch.
• Score: 13.969579728583248
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Decoder-only language models, such as GPT and LLaMA, generally decode on the last layer. Motivated by human's hierarchical thinking capability, we propose that a hierarchical decoder architecture could be built with different layers decoding texts simultaneously. Due to limited time and computationally resources, we choose to adapt a pretrained language model into this form of hierarchical decoder. Language heads of the last layer are copied to different selected intermediate layers, and fine-tuned with different task inputs. By thorough experiments, we validate that these selective intermediate layers could be adapted to speak meaningful and reasonable contents, and this paradigm of hierarchical decoder can obtain state-of-the-art performances on multiple tasks such as hierarchical text classification, classification-guided generation, and hierarchical text generation. HdLM outperforms all baselines on WoS, DBpedia, ESconv, EmpatheticDialogues, and several cognitive tests. We also provide thorough theoretical analysis to validate the convergence and computational savings of our methodology. This study suggests the possibility of a generalized hierarchical reasoner, pretraining from scratch.

Related papers

• Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining [58.69016084278948]
  We consider a hierarchical context-free grammar introduced by arXiv:2307.02129 and conjectured to separate deep and shallow networks.<n>We prove that, under mild conditions, a deep convolutional network can be efficiently trained to learn this function class.
  arXiv  Detail & Related papers  (2026-01-27T16:19:54Z)
• LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers [53.43862310647276]
  Large language models (LLMs) excel at natural language understanding and generation but remain vulnerable to factual errors.<n>We introduce a token-aware, layer-localized contrastive decoding method that aligns specific token types with their most influential transformer layers to improve factual generation.<n>Our method requires no additional training or model modification, and experiments demonstrate that our method consistently improves factuality across multiple LLMs and various benchmarks.
  arXiv  Detail & Related papers  (2025-07-06T14:35:43Z)
• Adaptive Large Language Models By Layerwise Attention Shortcuts [46.76681147411957]
  LLM-like setups allow the final layer to attend to all of the intermediate layers as it deems fit through the attention mechanism. We showcase four different datasets, namely acoustic tokens, natural language, and symbolic music, and we achieve superior performance for GPT-like architecture.
  arXiv  Detail & Related papers  (2024-09-17T03:46:01Z)
• Emergent Visual-Semantic Hierarchies in Image-Text Representations [13.300199242824934]
  We study the knowledge of existing foundation models, finding that they exhibit emergent understanding of visual-semantic hierarchies. We propose the Radial Embedding (RE) framework for probing and optimizing hierarchical understanding.
  arXiv  Detail & Related papers  (2024-07-11T14:09:42Z)
• A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition [41.05066959632938]
  Cross-lingual speech emotion recognition (SER) is important for a wide range of everyday applications. We propose a novel strategy called a layer-anchoring mechanism to facilitate emotion transfer in SER tasks. Our approach is evaluated using two distinct language affective corpora.
  arXiv  Detail & Related papers  (2024-07-06T05:56:55Z)
• Neural Architecture Search for Sentence Classification with BERT [4.862490782515929]
  We perform an AutoML search to find architectures that outperform the current single layer at only a small compute cost. We validate our classification architecture on a variety of NLP benchmarks from the GLUE dataset.
  arXiv  Detail & Related papers  (2024-03-27T13:25:43Z)
• LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model [70.14953942532621]
  Layer-collaborative diffusion model, named LayerDiff, is designed for text-guided, multi-layered, composable image synthesis. Our model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.
  arXiv  Detail & Related papers  (2024-03-18T16:28:28Z)
• Compositional Program Generation for Few-Shot Systematic Generalization [59.57656559816271]
  This study on a neuro-symbolic architecture called the Compositional Program Generator (CPG) CPG has three key features: textitmodularity, textitcomposition, and textitabstraction, in the form of grammar rules. It perfect achieves generalization on both the SCAN and COGS benchmarks using just 14 examples for SCAN and 22 examples for COGS.
  arXiv  Detail & Related papers  (2023-09-28T14:33:20Z)
• How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model [47.617093812158366]
  We introduce the Random Hierarchy Model: a family of synthetic tasks inspired by the hierarchical structure of language and images. We find that deep networks learn the task by developing internal representations invariant to exchanging equivalent groups. Our results indicate how deep networks overcome the curse of dimensionality by building invariant representations.
  arXiv  Detail & Related papers  (2023-07-05T09:11:09Z)
• VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation [91.39949385661379]
  VioLA is a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text. We first convert all the speech utterances to discrete tokens using an offline neural encoder. We further integrate task IDs (TID) and language IDs (LID) into the proposed model to enhance the modeling capability of handling different languages and tasks.
  arXiv  Detail & Related papers  (2023-05-25T14:39:47Z)
• Implant Global and Local Hierarchy Information to Sequence based Code Representation Models [25.776540440893257]
  We analyze how the complete hierarchical structure influences the tokens in code sequences and abstract this influence as a property of code tokens called hierarchical embedding. We propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model.
  arXiv  Detail & Related papers  (2023-03-14T12:01:39Z)
• MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding [53.03978356918377]
  spatial hierarchical relationships between content at different levels of granularity are crucial for document image understanding tasks. Existing methods learn features from either word-level or region-level but fail to consider both simultaneously. We propose MGDoc, a new multi-modal multi-granular pre-training framework that encodes page-level, region-level, and word-level information at the same time.
  arXiv  Detail & Related papers  (2022-11-27T22:47:37Z)
• Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification [23.719121637849806]
  We propose a hierarchy-guided Contrastive Learning (HGCLR) to embed the label hierarchy into a text encoder. During training, HGCLR constructs positive samples for input text under the guidance of the label hierarchy. After training, the HGCLR enhanced text encoder can dispense with the redundant hierarchy.
  arXiv  Detail & Related papers  (2022-03-08T03:21:45Z)
• Hierarchical Sketch Induction for Paraphrase Generation [79.87892048285819]
  We introduce Hierarchical Refinement Quantized Variational Autoencoders (HRQ-VAE), a method for learning decompositions of dense encodings. We use HRQ-VAE to encode the syntactic form of an input sentence as a path through the hierarchy, allowing us to more easily predict syntactic sketches at test time.
  arXiv  Detail & Related papers  (2022-03-07T15:28:36Z)
• Hierarchical Variational Memory for Few-shot Learning Across Domains [120.87679627651153]
  We introduce a hierarchical prototype model, where each level of the prototype fetches corresponding information from the hierarchical memory. The model is endowed with the ability to flexibly rely on features at different semantic levels if the domain shift circumstances so demand. We conduct thorough ablation studies to demonstrate the effectiveness of each component in our model.
  arXiv  Detail & Related papers  (2021-12-15T15:01:29Z)
• R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling [36.61173494449218]
  This paper proposes a model based on differentiable CKY style binary trees to emulate the composition process. We extend the bidirectional language model pre-training objective to this architecture, attempting to predict each word given its left and right abstraction nodes. To scale up our approach, we also introduce an efficient pruned tree induction algorithm to enable encoding in just a linear number of composition steps.
  arXiv  Detail & Related papers  (2021-07-02T11:00:46Z)
• An End-to-End Document-Level Neural Discourse Parser Exploiting Multi-Granularity Representations [24.986030179701405]
  We exploit robust representations derived from multiple levels of granularity across syntax and semantics. We incorporate such representations in an end-to-end encoder-decoder neural architecture for more resourceful discourse processing.
  arXiv  Detail & Related papers  (2020-12-21T08:01:04Z)
• Rethinking and Improving Natural Language Generation with Layer-Wise Multi-View Decoding [59.48857453699463]
  In sequence-to-sequence learning, the decoder relies on the attention mechanism to efficiently extract information from the encoder. Recent work has proposed to use representations from different encoder layers for diversified levels of information. We propose layer-wise multi-view decoding, where for each decoder layer, together with the representations from the last encoder layer, which serve as a global view, those from other encoder layers are supplemented for a stereoscopic view of the source sequences.
  arXiv  Detail & Related papers  (2020-05-16T20:00:39Z)
• A Multi-Perspective Architecture for Semantic Code Search [58.73778219645548]
  We propose a novel multi-perspective cross-lingual neural framework for code--text matching. Our experiments on the CoNaLa dataset show that our proposed model yields better performance than previous approaches.
  arXiv  Detail & Related papers  (2020-05-06T04:46:11Z)

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.