English
Related papers

Related papers: Draft-Conditioned Constrained Decoding for Structu…

200 papers

LLMs used for code generation are typically guided by engineering constraints--technology choices, dependency restrictions, and architectural patterns--expressed in verbose natural language. We investigate whether compact, structured…

Software Engineering · Computer Science 2026-04-23 Hanzhang Tang

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any…

Machine Learning · Computer Science 2025-07-15 Ziyi Chen , Xiaocong Yang , Jiacheng Lin , Chenkai Sun , Kevin Chen-Chuan Chang , Jie Huang

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

Machine Learning · Computer Science 2026-04-27 Henrijs Princis , Arindam Sharma , Cristina David

Large language models (LLMs) have revolutionized Text-to-SQL generation, allowing users to query structured data using natural language with growing ease. Yet, real-world deployment remains challenging, especially in complex or unseen…

Computation and Language · Computer Science 2026-05-01 Smit Jivani , Sarvam Maheshwari , Sunita Sarawagi

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft…

Machine Learning · Computer Science 2024-12-03 Zhuofan Wen , Shangtong Gui , Yang Feng

Code generation, symbolic math reasoning, and other tasks require LLMs to produce outputs that are both syntactically and semantically correct. Constrained LLM generation is a promising direction to enforce adherence to formal grammar, but…

Programming Languages · Computer Science 2025-09-08 Debangshu Banerjee , Tarun Suresh , Shubham Ugare , Sasa Misailovic , Gagandeep Singh

LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it…

Software Engineering · Computer Science 2025-10-01 Xunzhu Tang , Iyiola Emmanuel Olatunji , Tiezhu Sun , Jacques Klein , Tegawende F. Bissyande

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

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Computation and Language · Computer Science 2026-03-03 Jiebin Zhang , Zhenghan Yu , Liang Wang , Nan Yang , Eugene J. Yu , Zheng Li , Yifan Song , Dawei Zhu , Xingxing Zhang , Furu Wei , Sujian Li

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

Detoxification in large language models (LLMs) remains a significant research challenge. Existing decoding detoxification methods are all based on external constraints, which require additional resource overhead and lose generation fluency.…

Computation and Language · Computer Science 2025-10-16 Ming Dong , Jinkui Zhang , Bolong Zheng , Xinhui Tu , Po Hu , Tingting He

Speculative decoding is an inference-acceleration method for large language models (LLMs) where a small language model generates a draft-token sequence which is further verified by the target LLM in parallel. Recent works have advanced this…

Machine Learning · Computer Science 2024-03-06 Wonseok Jeon , Mukul Gagrani , Raghavv Goel , Junyoung Park , Mingu Lee , Christopher Lott

Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-formed markup. Constrained decoding approaches mitigate this problem by greedily restricting what…

Artificial Intelligence · Computer Science 2025-12-15 Kanghee Park , Jiayu Wang , Taylor Berg-Kirkpatrick , Nadia Polikarpova , Loris D'Antoni

Generating executable code from natural language instructions using Large Language Models (LLMs) poses challenges such as semantic ambiguity and understanding taskspecific contexts. To address these issues, we propose a system called…

Software Engineering · Computer Science 2025-03-25 Nirmal Joshua Kapu , Mihit Sreejith

Lossless speculative decoding accelerates target large language model (LLM) inference by employing a lightweight draft model for generating tree-structured candidates, which are subsequently verified in parallel by the target LLM.…

Computation and Language · Computer Science 2024-08-29 Lujun Gui , Bin Xiao , Lei Su , Weipeng Chen

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…

Computation and Language · Computer Science 2025-03-06 Guofeng Quan , Wenfeng Feng , Chuzhan Hao , Guochao Jiang , Yuewei Zhang , Hao Wang

Many recent approaches to structured NLP tasks use an autoregressive language model $M$ to map unstructured input text $x$ to output text $y$ representing structured objects (such as tuples, lists, trees, code, etc.), where the desired…

Computation and Language · Computer Science 2025-09-24 Marija Šakota , Robert West

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…

Computation and Language · Computer Science 2024-10-07 Lifu Tu , Semih Yavuz , Jin Qu , Jiacheng Xu , Rui Meng , Caiming Xiong , Yingbo Zhou

Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and do not scale well to multi-accelerator clusters used for…

Systems and Control · Electrical Eng. & Systems 2026-01-30 Junhao He , Feiran You , Hongyang Du