咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >LLaMA-LoRA Neural Prompt Engin... 收藏

LLaMA-LoRA Neural Prompt Engineering:A Deep Tuning Framework for Automatically Generating Chinese Text Logical Reasoning Thinking Chains

作     者:Songlin Chen Weicheng Wang Xiaoliang Chen Peng lu Zaiyan Yang Yajun Du 

作者机构:School of Computer and Software EngineeringXihua Universitychengdu 610039P.R.china Department of Computer Science and Operations ResearchUniversity of MontrealMontrealQC H3C3J7Canada College of Artificial intelligenceBeijing University of Posts and TelecommunicationsBeijing100876China 

出 版 物:《Data Intelligence》 (数据智能(英文))

年 卷 期:2024年第6卷第2期

页      面:375-408页

核心收录:

学科分类:081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术(可授工学、理学学位)] 

基  金:supported by the the Science and Technology Program of Sichuan Province(Grant no.2023YFS0424) the"Open bidding for selecting the best candidates"Science and Technology Project of Chengdu(Grant no.2023-JB00-00020-GX) the National Natural Science Foundation(Grant nos.61902324,11426179,and 61872298) 

主  题:Chinese natural language processing Neural prompt engineering Large language models Low-Rank adaptation Chain-of-thought 

摘      要:The exption of Chinese natural language processing(NLP)has stimulated research in the broader NLP ***,existing large language models have limitations in comprehending and reasoning in *** paper addresses these limitations by enhancing Chinese language models comprehension and reasoning capabilities while minimizing resource *** propose LLaMA-LoRA,a neural prompt engineering framework that builds upon the LLaMA-13B model and incorporates the Low-Rank Adaptation(LoRA)of Large Language Models technique for ***-of-Thought(CoT)are crucial for generating intermediate reasoning chains in language models,but their effectiveness can be limited by isolated language *** reasoning resulting from conventional prompts negatively impacts model *** prompts are introduced to encourage reasoning chain generation and accurate answer *** the model with an extensive corpus of Chinese CoT data enhances its comprehension and reasoning *** LLaMA-LoRA model demonstrates exceptional performance across numerous Chinese language tasks,surpassing benchmark performance achieved by related language models such as GPT-3.5,Chat-GLM,and OpenAssistant,delivering accurate,comprehensive,and professional *** availability of our open-source model code facilitates further research in the field of Chinese text logical reasoning thinking chains.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分