paper-with-me

홈 › Papers

Efficient Reasoning for LLMs through Speculative Chain-of-Thought

2025-04-27 · Jikai Wang, Juntao Li, Lijun Wu, Min Zhang

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 introduce significant reasoning costs and response latency. Existing methods for efficient reasoning mainly focus on reducing the number of model parameters or shortening the chain-of-thought length. In this paper, we introduce Speculative Chain-of-Thought (SCoT), which reduces reasoning latency from another perspective by accelerated average reasoning speed through large and small model collaboration. SCoT conducts thought-level drafting using a lightweight draft model. Then it selects the best CoT draft and corrects the error cases with the target model. The proposed thinking behavior alignment improves the efficiency of drafting and the draft selection strategy maintains the prediction accuracy for complex problems. Experimental results on GSM8K, MATH, GaoKao, CollegeMath and Olympiad datasets show that SCoT reduces reasoning latency by 48\%$\sim$66\% for Deepseek-R1-Distill-Qwen-32B while achieving near-target-model-level performance. Our code is available at https://github.com/Jikai0Wang/Speculative_CoT.

📄 PDF Abstract BibTeX arXiv:2504.19095

Code (1)

jikai0wang/speculative_cot 공식 구현 pytorch

Tasks

GSM8KMath

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Focus 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs

2025-02-17 · Yige Xu, Xu Guo, Zhiwei Zeng, Chunyan Miao

Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks by generating intermediate reasoning steps. However, most existing approaches focus on hard token decoding, which con…

parameter-efficient fine-tuning

SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding

2024-06-26 · Zhenglin Wang, Jialong Wu, Yilong Lai, Congzhi Zhang 외

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 …

GPUManagement

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

2026-05-11 · Shuzhang Zhong, Haochen Huang, Shengxuan Qiu, Pengfei Zuo 외 arxiv

Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving complex mathematical and programming tasks. However, its efficiency is co…

Scaling Laws for Speculative Decoding

2025-05-08 · Siyuan Yan, Mo Zhu, Guo-qing Jiang, Jianfei Wang 외

The escalating demand for efficient decoding in large language models (LLMs) is particularly critical for reasoning-intensive architectures like OpenAI-o3 and DeepSeek-R1, which depend on extended chain-of-thought reason…

Accelerating Large Language Model Reasoning via Speculative Search

2025-05-03 · Zhihai Wang, Jie Wang, Jilai Pan, Xilin Xia 외

Tree-search-based reasoning methods have significantly enhanced the reasoning capability of large language models (LLMs) by facilitating the exploration of multiple intermediate reasoning steps, i.e., thoughts. However, …

Language ModelingLanguage ModellingLarge Language Model