English
Related papers

Related papers: ConfSpec: Efficient Step-Level Speculative Reasoni…

200 papers

Large reasoning language models such as OpenAI-o1 and Deepseek-R1 have recently attracted widespread attention due to their impressive task-solving abilities. However, the enormous model size and the generation of lengthy thought chains…

Computation and Language · Computer Science 2025-05-27 Jikai Wang , Juntao Li , Jianye Hou , Bowen Yan , Lijun Wu , Min Zhang

Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribution. While…

Machine Learning · Computer Science 2025-07-08 Valentin De Bortoli , Alexandre Galashov , Arthur Gretton , Arnaud Doucet

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

Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. However, existing approaches face a fundamental credit assignment problem: methods like…

Computation and Language · Computer Science 2026-04-02 Chris Samarinas , Haw-Shiuan Chang , Hamed Zamani

Neural reasoning accuracy improves when generating intermediate reasoning steps. However, the source of this improvement is yet unclear. Here, we investigate and factorize the benefit of generating intermediate steps for symbolic reasoning.…

Artificial Intelligence · Computer Science 2023-02-17 Yoichi Aoki , Keito Kudo , Tatsuki Kuribayashi , Ana Brassard , Masashi Yoshikawa , Keisuke Sakaguchi , Kentaro Inui

Humans have a powerful and mysterious capacity to reason. Working through a set of mental steps enables us to make inferences we would not be capable of making directly even though we get no additional data from the world. Similarly, when…

Artificial Intelligence · Computer Science 2023-11-06 Ben Prystawski , Michael Y. Li , Noah D. Goodman

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

Large reasoning language models are typically run with fixed inference budgets, which can waste computation or terminate reasoning prematurely. We introduce Certainty-Guided Reasoning (CGR), a model-agnostic adaptive inference procedure…

Artificial Intelligence · Computer Science 2026-02-10 João Paulo Nogueira , Wentao Sun , Alonso Silva , Laith Zumot

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…

Computation and Language · Computer Science 2026-04-28 Han Wang , Xiaodong Yu , Jialian Wu , Jiang Liu , Ximeng Sun , Mohit Bansal , Zicheng Liu

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as…

Computation and Language · Computer Science 2025-06-06 Chengwu Liu , Ye Yuan , Yichun Yin , Yan Xu , Xin Xu , Zaoyu Chen , Yasheng Wang , Lifeng Shang , Qun Liu , Ming Zhang

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…

Artificial Intelligence · Computer Science 2026-02-20 Mert Cemri , Nived Rajaraman , Rishabh Tiwari , Xiaoxuan Liu , Kurt Keutzer , Ion Stoica , Kannan Ramchandran , Ahmad Beirami , Ziteng Sun

While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly bounded by the token acceptance rate. Prevalent methods…

Machine Learning · Computer Science 2024-10-16 Yunfan Xiong , Ruoyu Zhang , Yanzeng Li , Tianhao Wu , Lei Zou

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the…

Computation and Language · Computer Science 2026-04-10 Ziyi Wang , Siva Rajesh Kasa , Ankith M S , Santhosh Kumar Kasa , Jiaru Zou , Sumit Negi , Ruqi Zhang , Nan Jiang , Qifan Song

Ensuring the reliability of Large Language Models (LLMs) in complex reasoning tasks remains a formidable challenge, particularly in scenarios that demand precise mathematical calculations and knowledge-intensive open-domain generation. In…

Machine Learning · Computer Science 2025-05-27 Ali Razghandi , Seyed Mohammad Hadi Hosseini , Mahdieh Soleymani Baghshah

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Machine Learning · Computer Science 2025-05-27 Yixuan Wang , Yijun Liu , Shiyu ji , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

We propose Speculative Decoding (SpecDec), for the first time ever, to formally study exploiting the idea of speculative execution to accelerate autoregressive (AR) decoding. Speculative Decoding has two innovations: Spec-Drafter -- an…

Computation and Language · Computer Science 2023-10-31 Heming Xia , Tao Ge , Peiyi Wang , Si-Qing Chen , Furu Wei , Zhifang Sui

Test-time compute methods can significantly improve the reasoning capabilities and problem-solving accuracy of large language models (LLMs). However, these approaches require substantially more computational resources, with most compute…

Computation and Language · Computer Science 2026-01-28 Xianzhi Li , Ethan Callanan , Abdellah Ghassel , Xiaodan Zhu

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We…

Artificial Intelligence · Computer Science 2026-05-13 Wenkai Li , Fan Yang , Ananya Hazarika , Shaunak A. Mehta , Koichi Onoue

The practice of speculative decoding, whereby inference is probabilistically supported by a smaller, cheaper, ``drafter'' model, has become a standard technique for systematically reducing the decoding time of large language models. This…

Computation and Language · Computer Science 2025-10-03 Jameson Sandler , Ahmet Üstün , Marco Romanelli , Sara Hooker , Ferdinando Fioretto

Inference-time computation has emerged as a promising scaling axis for improving large language model reasoning. However, despite yielding impressive performance, the optimal allocation of inference-time computation remains poorly…

Machine Learning · Computer Science 2026-01-12 Parsa Mirtaheri , Ezra Edelman , Samy Jelassi , Eran Malach , Enric Boix-Adsera