Výsledky vyhledávání - "YANG Xiaocong"

Report

Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval

Autor: Yang, Xiaocong, Lin, Jiacheng, Wang, Ziqi, Zhai, Chengxiang

Large language models (LLMs) are known to struggle with complicated reasoning tasks such as math word problems (MWPs). In this paper, we present how analogy from similarly structured questions can improve LLMs' problem-solving capabilities for MWPs.

Externí odkaz: http://arxiv.org/abs/2411.16454

Zobrazit plný text záznamu

Report

Cascade Speculative Drafting for Even Faster LLM Inference

Autor: Chen, Ziyi, Yang, Xiaocong, Lin, Jiacheng, Sun, Chenkai, Chang, Kevin Chen-Chuan, Huang, Jie

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 acceptance by the

Externí odkaz: http://arxiv.org/abs/2312.11462

Zobrazit plný text záznamu

Akademický článek

Biologically inspired adaptive crack network reconstruction based on slime mould algorithm.

Autor: Chen, Zeng^1,2,3 (AUTHOR) zschenzeng@126.com, Yang, Xiaocong^1,2 (AUTHOR), Wang, Ping¹ (AUTHOR), Yu, Shibo¹ (AUTHOR), Chen, Lu¹ (AUTHOR)

Publikováno v: Scientific Reports. 11/6/2024, Vol. 14 Issue 1, p1-14. 14p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

Parameter-Efficient Tuning with Special Token Adaptation

Autor: Yang, Xiaocong, Huang, James Y., Zhou, Wenxuan, Chen, Muhao

Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks. In this work, we introduce PASTA, in which we only modify the special token representations (e.g., [SEP] and [CLS] in

Externí odkaz: http://arxiv.org/abs/2210.04382

Zobrazit plný text záznamu