English
Related papers

Related papers: Draft-Conditioned Constrained Decoding for Structu…

200 papers

Large language models (LLMs) have shown remarkable success across a wide range of natural language generation tasks, where proper prompt designs make great impacts. While existing prompting methods are normally restricted to providing…

Computation and Language · Computer Science 2023-06-01 Bei Li , Rui Wang , Junliang Guo , Kaitao Song , Xu Tan , Hany Hassan , Arul Menezes , Tong Xiao , Jiang Bian , JingBo Zhu

Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncertainty across prompts and individual decoding steps. We…

Machine Learning · Computer Science 2026-03-17 Chloe H. Su , Zhe Ye , Samuel Tenka , Aidan Yang , Soonho Kong , Udaya Ghai

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

Language Models (LMs) are increasingly used in applications where generated outputs must satisfy strict semantic or syntactic constraints. Existing approaches to constrained generation fall along a spectrum: greedy constrained decoding…

Artificial Intelligence · Computer Science 2025-10-03 Paweł Parys , Sairam Vaidya , Taylor Berg-Kirkpatrick , Loris D'Antoni

Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This paper targets on-device and low-cost small language model (SLM) deployments, where…

Machine Learning · Computer Science 2026-05-27 Jaideep Ray

We present a comprehensive evaluation of structured decoding for text-to-table generation with large language models (LLMs). While previous work has primarily focused on unconstrained generation of tables, the impact of enforcing structural…

Computation and Language · Computer Science 2025-08-25 Julian Oestreich , Lydia Müller

Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency. However, its utility is limited by a fundamental…

Computation and Language · Computer Science 2026-05-05 Sibo Xiao , Jinyuan Fu , Zhongle Xie , Lidan Shou

Large language models typically generate tokens autoregressively, using each token as input for the next. Recent work on Speculative Decoding has sought to accelerate this process by employing a smaller, faster draft model to more quickly…

Computation and Language · Computer Science 2024-10-24 Bradley McDanel

Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level…

Computation and Language · Computer Science 2025-02-26 Yanwen Huang , Yong Zhang , Ning Cheng , Zhitao Li , Shaojun Wang , Jing Xiao

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the…

Machine Learning · Computer Science 2026-04-24 Hongyi Liu , Jiaji Huang , Zhen Jia , Youngsuk Park , Yu-Xiang Wang

Large Language Models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require lengthy prompts, which increase computational costs and can…

Computation and Language · Computer Science 2025-04-16 Jinwu Hu , Wei Zhang , Yufeng Wang , Yu Hu , Bin Xiao , Mingkui Tan , Qing Du

We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents…

Reliably generating structured outputs has become a critical capability for modern language model (LM) applications. Constrained decoding has emerged as the dominant technology across sectors for enforcing structured outputs during…

Computation and Language · Computer Science 2025-02-28 Saibo Geng , Hudson Cooper , Michał Moskal , Samuel Jenkins , Julian Berman , Nathan Ranchin , Robert West , Eric Horvitz , Harsha Nori

Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality…

Computation and Language · Computer Science 2024-04-17 Neha Gupta , Harikrishna Narasimhan , Wittawat Jitkrittum , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar

We study the task of conducting structured reasoning as generating a reasoning graph from natural language input using large language models (LLMs). Previous approaches have explored various prompting schemes, yet they suffer from error…

Computation and Language · Computer Science 2024-06-04 Inderjeet Nair , Lu Wang

Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored. We introduce DREAM, a novel…

Computation and Language · Computer Science 2025-10-24 Yunhai Hu , Tianhua Xia , Zining Liu , Rahul Raman , Xingyu Liu , Bo Bao , Eric Sather , Vithursan Thangarasa , Sai Qian Zhang

Graph model generation from natural language description is an important task with many applications in software engineering. With the rise of large language models (LLMs), there is a growing interest in using LLMs for graph model…

Software Engineering · Computer Science 2025-08-04 Boqi Chen , Ou Wei , Bingzhou Zheng , Gunter Mussbacher

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capability for large language models (LLMs). Speculative decoding is one of the most direct and…

Machine Learning · Computer Science 2025-12-03 Zhendong Tan , Xingjun Zhang , Chaoyi Hu , Junjie Peng , Kun Xia

A common practice in large language model (LLM) usage for complex analytical tasks such as code generation, is to sample a solution for the entire task within the model's context window. Previous works have shown that subtask decomposition…

Artificial Intelligence · Computer Science 2025-02-03 Yotam Wolf , Binyamin Rothberg , Dorin Shteyman , Amnon Shashua