SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context

• URL: http://arxiv.org/abs/2408.00655v5
• Date: Wed, 14 Aug 2024 07:34:44 GMT
• Title: SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context
• Authors: Hongjun An, Yifan Chen, Zhe Sun, Xuelong Li,
• Abstract summary: We present Sentence Variational Autoencoder (SentenceVAE), which includes a Sentence to compress multiple tokens in a sentence into a single token, and a Sentence Decoder to reconstruct it. The proposed method can accelerate inference speed by 204365%, reduce perplexity (PPL) to 4675% of its original metric, and decrease memory overhead by 8691% for the equivalent context length.
• Score: 49.9628075245959
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed. In this paper, we introduce a novel inference methodology termed next-sentence prediction, aiming at enhancing the inference efficiency of LLMs. We present Sentence Variational Autoencoder (SentenceVAE), which includes a Sentence Encoder to compress multiple tokens in a sentence into a single token, and a Sentence Decoder to reconstruct it. By integrating SentenceVAE into the input and output layers of LLMs, we develop Sentence-level LLMs (SLLMs) that employ a sentence-by-sentence inference method. In addition, the SentenceVAE module of SLLMs can maintain the integrity of the original semantic content by segmenting the context into sentences, thereby improving accuracy while boosting inference speed. Moreover, compared to previous LLMs, SLLMs process fewer tokens over equivalent context length, significantly reducing memory demands for self-attention computation and facilitating the handling of longer context. Extensive experiments on Wanjuan dataset have revealed that the proposed method can accelerate inference speed by 204~365%, reduce perplexity (PPL) to 46~75% of its original metric, and decrease memory overhead by 86~91% for the equivalent context length, compared to previous token-by-token methods.

Related papers

• Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference [16.830389144259584]
  We propose context-aware prompt compression (CPC), a sentence-level prompt compression technique. Key innovation is a novel context-aware sentence encoder that provides a relevance score for each sentence for a given question. Our method considerably outperforms prior works on prompt compression on benchmark datasets.
  arXiv  Detail & Related papers  (2024-09-02T13:02:51Z)
• Graph-Structured Speculative Decoding [52.94367724136063]
  Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models. We introduce an innovative approach utilizing a directed acyclic graph (DAG) to manage the drafted hypotheses. We observe a remarkable speedup of 1.73$times$ to 1.96$times$, significantly surpassing standard speculative decoding.
  arXiv  Detail & Related papers  (2024-07-23T06:21:24Z)
• UIO-LLMs: Unbiased Incremental Optimization for Long-Context LLMs [111.12010207132204]
  UIO-LLMs is an incremental optimization approach for memory-enhanced transformers under long-context settings. We refine the training process using the Truncated Backpropagation Through Time (TBPTT) algorithm. UIO-LLMs successfully handle long context, such as extending the context window of Llama2-7b-chat from 4K to 100K tokens with minimal 2% additional parameters.
  arXiv  Detail & Related papers  (2024-06-26T08:44:36Z)
• Nearest Neighbor Speculative Decoding for LLM Generation and Attribution [87.3259169631789]
  Nearest Speculative Decoding (NEST) is capable of incorporating real-world text spans of arbitrary length into the LM generations and providing attribution to their sources. NEST significantly enhances the generation quality and attribution rate of the base LM across a variety of knowledge-intensive tasks. In addition, NEST substantially improves the generation speed, achieving a 1.8x speedup in inference time when applied to Llama-2-Chat 70B.
  arXiv  Detail & Related papers  (2024-05-29T17:55:03Z)
• Training LLMs over Neurally Compressed Text [55.11828645767342]
  This paper explores the idea of training large language models (LLMs) over highly compressed text. We propose Equal-Info Windows, a novel compression technique whereby text is segmented into blocks that each compress to the same bit length. We demonstrate effective learning over neurally compressed text that improves with scale, and outperforms byte-level baselines by a wide margin on perplexity and inference speed benchmarks.
  arXiv  Detail & Related papers  (2024-04-04T17:48:28Z)
• CLLMs: Consistency Large Language Models [18.17892007267927]
  Jacobi decoding achieves little speedup compared to traditional autoregressive (AR) decoding. We develop a new approach aimed at realizing fast convergence from any state to the fixed point on a Jacobi trajectory.
  arXiv  Detail & Related papers  (2024-02-28T20:17:04Z)
• Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens [15.566726645722657]
  We propose a novel framework specifically designed for speculative sampling. Within this framework, we introduce a lightweight draft model that effectively utilizes previously generated tokens to predict subsequent words. We demonstrate impressive results, achieving an average latency speedup ratio of 2.7x compared to the vanilla auto-regressive decoding approach.
  arXiv  Detail & Related papers  (2024-02-24T08:10:39Z)
• Alleviating Over-smoothing for Unsupervised Sentence Representation [96.19497378628594]
  We present a Simple method named Self-Contrastive Learning (SSCL) to alleviate this issue. Our proposed method is quite simple and can be easily extended to various state-of-the-art models for performance boosting.
  arXiv  Detail & Related papers  (2023-05-09T11:00:02Z)
• Span Fine-tuning for Pre-trained Language Models [43.352833140317486]
  This paper presents a novel span fine-tuning method for PrLMs. Any sentences processed by the PrLM will be segmented into multiple spans according to a pre-sampled dictionary. Experiments on GLUE benchmark show that the proposed span fine-tuning method significantly enhances the PrLM.
  arXiv  Detail & Related papers  (2021-08-29T14:11:38Z)
• Enhancing Pre-trained Language Model with Lexical Simplification [41.34550924004487]
  lexical simplification (LS) is a recognized method to reduce such lexical diversity. We propose a novel approach which can effectively improve the performance of PrLMs in text classification.
  arXiv  Detail & Related papers  (2020-12-30T07:49:00Z)

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.