English
Related papers

Related papers: REST: Retrieval-Based Speculative Decoding

200 papers

Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs). However, this improved accuracy comes at the cost of high…

Machine Learning · Computer Science 2025-05-20 Rui Pan , Yinwei Dai , Zhihao Zhang , Gabriele Oliaro , Zhihao Jia , Ravi Netravali

Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…

Machine Learning · Computer Science 2025-12-09 Yize Wu , Ke Gao , Ling Li , Yanjun Wu

Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of…

Computation and Language · Computer Science 2024-12-18 Zhenglin Wang , Jialong Wu , Yilong Lai , Congzhi Zhang , Deyu Zhou

Self-training (ST) has come to fruition in language understanding tasks by producing pseudo labels, which reduces the labeling bottleneck of language model fine-tuning. Nevertheless, in facilitating semi-supervised controllable language…

Computation and Language · Computer Science 2023-06-21 Yuxi Feng , Xiaoyuan Yi , Laks V. S. Lakshmanan , Xing Xie

LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to speculatively generate multiple tokens, which are then verified in parallel by a target…

Computation and Language · Computer Science 2026-04-21 Sungkyun Kim , Jaemin Kim , Dogyung Yoon , Jiho Shin , Junyeol Lee , Jiwon Seo

In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models. We first conduct a comprehensive analysis of existing models and identify their limitations in in-context learning,…

Computation and Language · Computer Science 2024-08-20 Jie Huang , Wei Ping , Peng Xu , Mohammad Shoeybi , Kevin Chen-Chuan Chang , Bryan Catanzaro

Large Language Models (LLMs) have become essential in advancing natural language processing (NLP) tasks, but their sequential token generation limits inference speed. Multi-Draft Speculative Decoding (MDSD) offers a promising solution by…

Computation and Language · Computer Science 2024-11-11 Ryan Sun , Tianyi Zhou , Xun Chen , Lichao Sun

This paper is written because I receive several inquiry emails saying it is hard to achieve good results when applying token repetition learning techniques. If REP (proposed by me) or Pointer-Mixture (proposed by Jian Li) is directly…

Software Engineering · Computer Science 2020-06-25 Yixiao Yang

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 focus on Text-to-SQL semantic parsing from the perspective of retrieval-augmented generation. Motivated by challenges related to the size of commercial database schemata and the deployability of business intelligence solutions, we…

Computation and Language · Computer Science 2024-11-05 Zhili Shen , Pavlos Vougiouklis , Chenxin Diao , Kaustubh Vyas , Yuanyi Ji , Jeff Z. Pan

Large reasoning models improve accuracy by producing long reasoning traces, but this inflates latency and cost, motivating inference-time efficiency. We propose Retrieval-of-Thought (RoT), which reuses prior reasoning as composable…

Artificial Intelligence · Computer Science 2026-05-12 Ammar Ahmed , Azal Ahmad Khan , Ayaan Ahmad , Sheng Di , Zirui Liu , Ali Anwar

Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To…

Computation and Language · Computer Science 2022-11-16 Kalpesh Krishna , Yapei Chang , John Wieting , Mohit Iyyer

Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a…

Computation and Language · Computer Science 2024-01-15 Sen Yang , Shujian Huang , Xinyu Dai , Jiajun Chen

Many language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to further progress, but ensembling generation models is…

Computation and Language · Computer Science 2022-10-31 Jungo Kasai , Keisuke Sakaguchi , Ronan Le Bras , Hao Peng , Ximing Lu , Dragomir Radev , Yejin Choi , Noah A. Smith

Speculative decoding has become the standard approach for accelerating Large Language Model (LLM) inference. It exploits a lossless draft-then-verify procedure to circumvent the latency of autoregressive decoding, achieving impressive…

Computation and Language · Computer Science 2025-11-05 Jameson Sandler , Jacob K. Christopher , Thomas Hartvigsen , Ferdinando Fioretto

Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from frequent false rejections, particularly when draft models produce semantically correct but…

Computation and Language · Computer Science 2026-04-16 Xuwen Zhou , Fangxin Liu , Chao Wang , Xiao Zheng , Hao Zheng , Min He , Li Jiang , Haibing Guan

Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Alloy Das , Sanket Biswas , Prasun Roy , Subhankar Ghosh , Umapada Pal , Michael Blumenstein , Josep Lladós , Saumik Bhattacharya

Speculative Decoding (SD) accelerates inference in large language models by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, the throughput gains of SD are fundamentally limited by a…

Computation and Language · Computer Science 2025-10-16 Sanghyun Byun , Mohanad Odema , Jung Ick Guack , Baisub Lee , Jacob Song , Woo Seong Chung

Traditional session types prescribe bidirectional communication protocols for concurrent computations, where well-typed programs are guaranteed to adhere to the protocols. However, simple session types cannot capture properties beyond the…

Programming Languages · Computer Science 2023-06-22 Ankush Das , Frank Pfenning

We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existing works that aim to build entire repositories for execution,…

Computation and Language · Computer Science 2025-03-11 Yiqing Xie , Alex Xie , Divyanshu Sheth , Pengfei Liu , Daniel Fried , Carolyn Rose