English
Related papers

Related papers: Parallel Decoding via Hidden Transfer for Lossless…

200 papers

In this paper, we propose a two-phase training approach where pre-trained large language models are continually pre-trained on parallel data and then supervised fine-tuned with a small amount of high-quality parallel data. To investigate…

Computation and Language · Computer Science 2024-07-04 Minato Kondo , Takehito Utsuro , Masaaki Nagata

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits…

Computation and Language · Computer Science 2026-04-22 Zhenbang Du , Kejing Xia , Xinrui Zhong , Yonggan Fu , Nicolai Oswald , Binfei Ji , Brucek Khailany , Pavlo Molchanov , Yingyan Lin

Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token…

Computation and Language · Computer Science 2024-07-03 Parsa Kavehzadeh , Mohammadreza Pourreza , Mojtaba Valipour , Tinashu Zhu , Haoli Bai , Ali Ghodsi , Boxing Chen , Mehdi Rezagholizadeh

In decoder-based LLMs, the representation of a given layer serves two purposes: as input to the next layer during the computation of the current token; and as input to the attention mechanism of future tokens. In this work, we show that the…

Computation and Language · Computer Science 2024-11-01 Amit Ben-Artzy , Roy Schwartz

This study introduces a groundbreaking approach to simultaneous interpretation by directly leveraging the predictive capabilities of Large Language Models (LLMs). We present a novel algorithm that generates real-time translations by…

Computation and Language · Computer Science 2024-07-22 Kurando Iida , Kenjiro Mimura , Nobuo Ito

Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target model. However, existing draft model training objectives are…

Computation and Language · Computer Science 2026-05-12 Zihao An , Taichi Liu , Ziqiong Liu , Dong Li , Ruofeng Liu , Emad Barsoum

We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of…

Computation and Language · Computer Science 2023-02-03 Charlie Chen , Sebastian Borgeaud , Geoffrey Irving , Jean-Baptiste Lespiau , Laurent Sifre , John Jumper

We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references. LLMA is motivated by the observation that there are abundant identical text spans between the decoding result by an LLM and the…

Computation and Language · Computer Science 2023-04-11 Nan Yang , Tao Ge , Liang Wang , Binxing Jiao , Daxin Jiang , Linjun Yang , Rangan Majumder , Furu Wei

While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…

Computation and Language · Computer Science 2021-07-26 Edoardo Maria Ponti , Julia Kreutzer , Ivan Vulić , Siva Reddy

The performance of existing text style transfer models is severely limited by the non-parallel datasets on which the models are trained. In non-parallel datasets, no direct mapping exists between sentences of the source and target style;…

Computation and Language · Computer Science 2022-04-19 Ruibo Liu , Chongyang Gao , Chenyan Jia , Guangxuan Xu , Soroush Vosoughi

Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these strategies aim to transform the raw probability distributions…

Computation and Language · Computer Science 2024-12-17 Esteban Garces Arias , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a…

Computation and Language · Computer Science 2024-02-08 Yutian Chen , Hao Kang , Vivian Zhai , Liangze Li , Rita Singh , Bhiksha Raj

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-13 Ditto PS , Jithin VG , Adarsh MS

Generative Large Language Models (LLMs) have achieved remarkable advancements in various NLP tasks. However, these advances have not been reflected in the translation task, especially those with moderate model sizes (i.e., 7B or 13B…

Computation and Language · Computer Science 2024-02-07 Haoran Xu , Young Jin Kim , Amr Sharaf , Hany Hassan Awadalla

Generally, the decoder-only large language models (LLMs) are adapted to context-aware neural machine translation (NMT) in a concatenating way, where LLMs take the concatenation of the source sentence (i.e., intra-sentence context) and the…

Computation and Language · Computer Science 2024-09-24 Xinglin Lyu , Junhui Li , Yanqing Zhao , Min Zhang , Daimeng Wei , Shimin Tao , Hao Yang , Min Zhang

Existing work on prompt compression for Large Language Models (LLM) focuses on lossy methods that try to maximize the retention of semantic information that is relevant to downstream tasks while significantly reducing the sequence length.…

Computation and Language · Computer Science 2025-08-22 John Harvill , Ziwei Fan , Hao Wang , Luke Huan , Anoop Deoras , Yizhou Sun , Hao Ding

The efficiency of large language models (LLMs) is fundamentally limited by their sequential, token-by-token generation process. We argue that overcoming this bottleneck requires a new design axis for LLM scaling: increasing the semantic…

Computation and Language · Computer Science 2025-11-03 Chenze Shao , Darren Li , Fandong Meng , Jie Zhou

Simultaneous speech translation is an essential communication task difficult for humans whereby a translation is generated concurrently with oncoming speech inputs. For such a streaming task, transformers using block processing to break an…

Computation and Language · Computer Science 2023-07-06 Matthew Raffel , Lizhong Chen

This paper introduces the idea of applying signal processing inside a Large Language Model (LLM). With the recent explosion of generative AI, our work can help bridge two fields together, namely the field of signal processing and large…

Computation and Language · Computer Science 2024-09-19 Prateek Verma , Mert Pilanci

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Computation and Language · Computer Science 2024-05-24 Yufan Jiang , Qiaozhi He , Xiaomin Zhuang , Zhihua Wu , Kunpeng Wang , Wenlai Zhao , Guangwen Yang