Hierarchical Skip Decoding for Efficient Autoregressive Text Generation

• URL: http://arxiv.org/abs/2403.14919v1
• Date: Fri, 22 Mar 2024 02:44:05 GMT
• Title: Hierarchical Skip Decoding for Efficient Autoregressive Text Generation
• Authors: Yunqi Zhu, Xuebing Yang, Yuanyuan Wu, Wensheng Zhang,
• Abstract summary: We propose a novel decoding strategy named Hierarchical Skip Decoding (HSD) for efficient autoregressive text generation. With almost half of the layers skipped, HSD can sustain 90% of the text quality compared to vanilla autoregressive decoding.
• Score: 9.16858904192541
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the inference stage. In this work, we propose a novel decoding strategy named Hierarchical Skip Decoding (HSD) for efficient autoregressive text generation. Different from existing methods that require additional trainable components, HSD is a plug-and-play method applicable to autoregressive text generation models, it adaptively skips decoding layers in a hierarchical manner based on the current sequence length, thereby reducing computational workload and allocating computation resources. Comprehensive experiments on five text generation datasets with pre-trained language models demonstrate HSD's advantages in balancing efficiency and text quality. With almost half of the layers skipped, HSD can sustain 90% of the text quality compared to vanilla autoregressive decoding, outperforming the competitive approaches.

Related papers

• Synthetic Text Generation for Training Large Language Models via Gradient Matching [27.74603049449281]
  We propose the first theoretically rigorous approach for generating synthetic human-readable text. In doing so, the generated synthetic text can guarantee convergence of the model to a close neighborhood of the solution obtained by fine-tuning on real data.
  arXiv  Detail & Related papers  (2025-02-24T19:49:15Z)
• Mind the Gap: A Generalized Approach for Cross-Modal Embedding Alignment [0.0]
  Retrieval-Augmented Generation (RAG) systems retrieve context across different text modalities due to semantic gaps. We introduce a generalized projection-based method, inspired by adapter modules in transfer learning, that efficiently bridges these gaps. Our approach emphasizes speed, accuracy, and data efficiency, requiring minimal resources for training and inference.
  arXiv  Detail & Related papers  (2024-10-30T20:28:10Z)
• Enhancing Text Generation in Joint NLG/NLU Learning Through Curriculum Learning, Semi-Supervised Training, and Advanced Optimization Techniques [0.0]
  This research paper developed a novel approach to improve text generation in the context of joint Natural Language Generation (NLG) and Natural Language Understanding (NLU) learning. The data is prepared by gathering and preprocessing annotated datasets, including cleaning, tokenization, stemming, and stop-word removal. Transformer-based encoders and decoders, capturing long range dependencies and improving source-target sequence modelling. Reinforcement learning with policy gradient techniques, semi-supervised training, improved attention mechanisms, and differentiable approximations are employed to fine-tune the models and handle complex linguistic tasks effectively.
  arXiv  Detail & Related papers  (2024-10-17T12:43:49Z)
• Cascade Reward Sampling for Efficient Decoding-Time Alignment [18.537156067913283]
  We proposeCARDS to generate high-reward and high-likelihood text. CARDS guarantees the generation of high-reward and high-likelihood text with significantly low costs. experiments demonstrate substantial gains in both generation efficiency and alignment ratings.
  arXiv  Detail & Related papers  (2024-06-24T04:08:35Z)
• Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs [57.27982780697922]
  Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process. This paper introduces Lexical Unit Decoding, a novel decoding methodology implemented in a data-driven manner.
  arXiv  Detail & Related papers  (2024-05-24T04:35:13Z)
• Improving Text Embeddings with Large Language Models [59.930513259982725]
  We introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. We leverage proprietary LLMs to generate diverse synthetic data for hundreds of thousands of text embedding tasks across 93 languages. Experiments demonstrate that our method achieves strong performance on highly competitive text embedding benchmarks without using any labeled data.
  arXiv  Detail & Related papers  (2023-12-31T02:13:18Z)
• Successor Features for Efficient Multisubject Controlled Text Generation [48.37713738712319]
  We introduce SF-GEN, which is grounded in two primary concepts: successor features (SFs) and language model rectification. SF-GEN seamlessly integrates the two to enable dynamic steering of text generation with no need to alter the LLM's parameters. To the best of our knowledge, our research represents the first application of successor features in text generation.
  arXiv  Detail & Related papers  (2023-11-03T00:17:08Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)
• Text Simplification by Tagging [21.952293614293392]
  We present TST, a simple and efficient Text Simplification system based on sequence Tagging. Our system makes simplistic data augmentations and tweaks in training and inference on a pre-existing system. It achieves faster inference speeds by over 11 times than the current state-of-the-art text simplification system.
  arXiv  Detail & Related papers  (2021-03-08T20:57:55Z)
• Fast Sequence Generation with Multi-Agent Reinforcement Learning [40.75211414663022]
  Non-autoregressive decoding has been proposed in machine translation to speed up the inference time by generating all words in parallel. We propose a simple and efficient model for Non-Autoregressive sequence Generation (NAG) with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL) On MSCOCO image captioning benchmark, our NAG method achieves a performance comparable to state-of-the-art autoregressive models, while brings 13.9x decoding speedup.
  arXiv  Detail & Related papers  (2021-01-24T12:16:45Z)
• Cascaded Text Generation with Markov Transformers [122.76100449018061]
  Two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependencies. This work proposes an autoregressive model with sub-linear parallel time generation. Noting that conditional random fields with bounded context can be decoded in parallel, we propose an efficient cascaded decoding approach for generating high-quality output. This approach requires only a small modification from standard autoregressive training, while showing competitive accuracy/speed tradeoff compared to existing methods on five machine translation datasets.
  arXiv  Detail & Related papers  (2020-06-01T17:52:15Z)
• POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training [93.79766670391618]
  We present POINTER, a novel insertion-based approach for hard-constrained text generation. The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner. The resulting coarse-to-fine hierarchy makes the generation process intuitive and interpretable.
  arXiv  Detail & Related papers  (2020-05-01T18:11:54Z)

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.