期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到794,844篇文章
< 1 2 … 250 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Green scheduling for LLM workloads with model and data reuse across geo-distributed data centers 认领 引用
1
作者 Hao Liu Xiaonyu Hu +3 位作者 Ran Wang Jie Hao Qiang Wu Hongke Zhang 《Digital Communications and Networks》 SCIE EI CSCD 2026年第2期236-251,共16页
The explosive proliferation of Large Language Models(LLMs)imposes significant energy and operational burdens on Geographically Distributed Data Centers(GDDCs),thereby demanding an efficient mechanism for LLMs task sch... The explosive proliferation of Large Language Models(LLMs)imposes significant energy and operational burdens on Geographically Distributed Data Centers(GDDCs),thereby demanding an efficient mechanism for LLMs task scheduling.While prior geo-distributed scheduling methods reduce cost and carbon emissions by exploiting regional heterogeneity,they largely overlook model and data reuse opportunities and the uncertainty of LLM execution times.In this paper,we introduce GCOS,to the best of our knowledge,the first green scheduling framework that incorporates a dual-cache system for both data and models,while jointly optimizing task assignment and cache migration.We firstly propose a dual-cache mechanism that decouples model and data caching to enable fine-grained reuse and minimize redundant transmissions.Subsequently,we propose the Multi-Agent Cache-aware Cooperative Scheduling(MACCS)algorithm,which leverages reinforcement learning to optimize task placement with a focus on minimizing both carbon emissions and cost.Additionally,we design a lightweight execution time predictor,DiPTree,to address the high variability in task execution times.Extensive experiments on real-world datasets demonstrate that GCOS reduces overall cost by up to 92.6%and carbon emissions by 90.3%,significantly outperforming existing baselines. 展开更多
关键词 Large language model Geographically distributed data center Green communication Task scheduling Multi-agent reinforcement learning
暂未订购 下载PDF
Integration of Large Language Models(LLMs)and Static Analysis for Improving the Efficacy of Security Vulnerability Detection in Source Code 认领 引用 被引量：1
2
作者 José Armando Santas Ciavatta Juan Ramón Bermejo Higuera +3 位作者 Javier Bermejo Higuera Juan Antonio Sicilia Montalvo Tomás Sureda Riera Jesús Pérez Melero 《Computers, Materials & Continua》 SCIE EI 2026年第3期351-390,共40页
As artificial Intelligence(AI)continues to expand exponentially,particularly with the emergence of generative pre-trained transformers(GPT)based on a transformer’s architecture,which has revolutionized data processin... As artificial Intelligence(AI)continues to expand exponentially,particularly with the emergence of generative pre-trained transformers(GPT)based on a transformer’s architecture,which has revolutionized data processing and enabled significant improvements in various applications.This document seeks to investigate the security vulnerabilities detection in the source code using a range of large language models(LLM).Our primary objective is to evaluate the effectiveness of Static Application Security Testing(SAST)by applying various techniques such as prompt persona,structure outputs and zero-shot.To the selection of the LLMs(CodeLlama 7B,DeepSeek coder 7B,Gemini 1.5 Flash,Gemini 2.0 Flash,Mistral 7b Instruct,Phi 38b Mini 128K instruct,Qwen 2.5 coder,StartCoder 27B)with comparison and combination with Find Security Bugs.The evaluation method will involve using a selected dataset containing vulnerabilities,and the results to provide insights for different scenarios according to the software criticality(Business critical,non-critical,minimum effort,best effort)In detail,the main objectives of this study are to investigate if large language models outperform or exceed the capabilities of traditional static analysis tools,if the combining LLMs with Static Application Security Testing(SAST)tools lead to an improvement and the possibility that local machine learning models on a normal computer produce reliable results.Summarizing the most important conclusions of the research,it can be said that while it is true that the results have improved depending on the size of the LLM for business-critical software,the best results have been obtained by SAST analysis.This differs in“NonCritical,”“Best Effort,”and“Minimum Effort”scenarios,where the combination of LLM(Gemini)+SAST has obtained better results. 展开更多
关键词 AI+SAST secure code LLM benchmarking LLM vulnerability detection
暂未订购 下载PDF
LLMKB:Large Language Models with Knowledge Base Augmentation for Conversational Recommendation 认领 引用
3
作者 FANG Xiu QIU Sijia +1 位作者 SUN Guohao LU Jinhu 《Journal of Donghua University(English Edition)》 CAS 2026年第1期91-103,共13页
Conversational recommender systems(CRSs)focus on refining preferences and providing personalized recommendations through natural language interactions and dialogue history.Large language models(LLMs)have shown outstan... Conversational recommender systems(CRSs)focus on refining preferences and providing personalized recommendations through natural language interactions and dialogue history.Large language models(LLMs)have shown outstanding performance across various domains,thereby prompting researchers to investigate their applicability in recommendation systems.However,due to the lack of task-specific knowledge and an inefficient feature extraction process,LLMs still have suboptimal performance in recommendation tasks.Therefore,external knowledge sources,such as knowledge graphs(KGs)and knowledge bases(KBs),are often introduced to address the issue of data sparsity.Compared to KGs,KBs possess higher retrieval efficiency,making them more suitable for scenarios where LLMs serve as recommenders.To this end,we introduce a novel framework integrating LLMs with KBs for enhanced retrieval generation,namely LLMKB.LLMKB initially leverages structured knowledge to create mapping dictionaries,extracting entity-relation information from heterogeneous knowledge to construct KBs.Then,LLMKB achieves the embedding calibration between user information representations and documents in KBs through retrieval model fine-tuning.Finally,LLMKB employs retrievalaugmented generation to produce recommendations based on fused text inputs,followed by post-processing.Experiment results on two public CRS datasets demonstrate the effectiveness of our framework.Our code is publicly available at the link:http://gffzze280b34df20547e2sk0npuwb0kbbk6qnc.ffgz.tsg.suse.edu.cn/LLMKB-6FD0. 展开更多
关键词 recommender system large language model(LLM) knowledge base(KB)
暂未订购 下载PDF
From LLM to Agent:A large-language-model-driven machine learning framework for catalyst design of MgH2dehydrogenation 认领 引用 被引量：1
4
作者 Tongao Yao Yang Yang +7 位作者 Jianghao Cai Rui Liu Zhaoyan Dong Xiaotian Tang Xuqiang Shao Zhengyang Gao Guangyao An Weijie Yang 《Journal of Magnesium and Alloys》 SCIE EI CAS CSCD 2026年第1期410-426,共17页
Magnesium hydride(MgH2),a promising high-capacity hydrogen storage material,is hindered by slow dehydrogenation kinetics.AIdriven catalyst discovery to address this is often hampered by the laborious extraction of ... Magnesium hydride(MgH2),a promising high-capacity hydrogen storage material,is hindered by slow dehydrogenation kinetics.AIdriven catalyst discovery to address this is often hampered by the laborious extraction of data from unstructured literature.To overcome this,we introduce a transformative“LLM to Agent”framework that synergistically integrates Large Language Models(LLMs)for automated data curation with Machine Learning(ML)for predictive design.We automatically constructed a comprehensive database of 809 MgH2catalysts(6555 data rows)with high fidelity and an~40-fold acceleration over manual methods.The resulting ML models achieved high accuracy(average R2>0.91)in predicting dehydrogenation temperature and activation energy,subsequently guiding a Genetic Algorithm(GA)in an exploratory inverse design that autonomously uncovered key design principles for high-performance catalysts.Encouragingly,a strong alignment was found between these AI-discovered principles and the design strategies of recently reported,state-of-the-art experimental systems,providing substantial evidence for the validity of our approach.The framework culminates in Cat-Advisor,a novel,domain-adapted multi-agent system.Cat-Advisor translates ML predictions and retrieval-augmented knowledge into actionable design guidance,demonstrating capabilities that surpass those of general-purpose LLMs in this specialized domain.This work delivers a practical AI toolkit for accelerated materials discovery and advances the emerging Agent-based paradigm for designing next-generation energy technologies. 展开更多
关键词 MgH2dehydrogenation Large language model Machine learning Genetic algorithm Catalyst design Hydrogen storage
暂未订购 下载PDF
LLM-Driven Cross-Flow Modeling for Network Attack Traffic Detection 认领 引用
5
作者 Aoran Huang Sinuo Zhang +2 位作者 Haoxiang Zhu Xiaojing Fan Huachun Zhou 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第7期1427-1458,共32页
In Future Mobile Internet and convergence application scenarios,existing network attack traffic detection methods are insufficient in characterizing cross-flow correlations and structural dependencies during the attac... In Future Mobile Internet and convergence application scenarios,existing network attack traffic detection methods are insufficient in characterizing cross-flow correlations and structural dependencies during the attack process,and therefore still have limited generalization ability in complex scenarios and unknown attack identification tasks.To address this issue,this paper proposes a cross-flow modeling large language model framework,which extends the traditional detection paradigm based on single-flow features to joint modeling oriented toward cross-flow context and relational structure.Specifically,this paper constructs cross-flow context through flow sorting,grouping,and cross-group sampling,and combines an inter-flow relation matrix with a dual-branch embedding mechanism to achieve structured representation and relation-aware modeling of network traffic;at the model level,by removing the causal mask and introducing a relation-aware bias into bidirectional self-attention,the representation capability of the large language model for complex attack behaviors and potential inter-flow dependencies is enhanced.Experimental results show that the proposed method overall outperforms traditional machine learning and deep learning baseline models,and demonstrates better stability and accuracy in tasks such as fine-grained classification,unknown attack identification,and cross-scenario generalization.Ablation experiments further verify the effectiveness of the proposed cross-flow context construction,dual-branch embedding,and relation-aware LLM adaptation,demonstrating that each component contributes to the overall detection performance and generalization ability.Our work shows that,after targeted structural adaptation,large language models can effectively serve non-text security tasks such as network traffic analysis,thereby supporting AI-driven security modeling for Future Mobile Internet environments. 展开更多
关键词 Large language models network traffic detection network security attention mechanism
暂未订购 下载PDF
STALAgent:A Multi-Agent System Based on Large Language Model(LLM)for Steel and Alloy Design 认领 引用
6
作者 Jiayi Qiu Youle Wang Lei Zhang 《Computers, Materials & Continua》 SCIE EI 2026年第10期434-454,共21页
The design of steel and alloy materials is of critical importance across a wide range of industrial applications;however,effective intelligent agent-based assistants for this domain remain limited.To address this gap,... The design of steel and alloy materials is of critical importance across a wide range of industrial applications;however,effective intelligent agent-based assistants for this domain remain limited.To address this gap,we introduce STALAgent,a large language model(LLM)-based multi-agent system specifically tailored for intelligent and automated design of steel and alloy materials.STALAgent is centered on an LLM brain with several key agents(e.g.,task assignment,semantic search,inverse design,and heat treatment simulation)that collectively form a closed-loop workflow from user query to material recommendation.This system leverages a CrewAI-based orchestrator to assign tasks and coordinate a suite of specialized agents,including tools for knowledge retrieval using a retrieval augmented generation(RAG),inverse materials design using variational encoder(VAE),and thermodynamic calculations using Pycalphad.Through case studies involving inverse alloy design tasks and knowledge-based steel design queries,we showcase the capacity of the LLM agent to offer effective and dependable guidance for steel and alloy material design.STALAgent is practical and scalable,serving as a supplementary tool for materials researchers and holding promise for extension to other materials science domains requiring scientific discovery and domain knowledge-intensive tasks. 展开更多
关键词 Agent LLM large language model materials informatics materials genome
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
7
《上海口腔医学》 CAS CSCD 2026年第4期392-392,共1页
AI署名权:LLMs,如ChatGPT、DeepSeek等,目前不符合作者署名标准,应在稿件的“方法”部分妥善标识LLM的使用,用于“AI辅助文稿编辑”目的的LLM(或其他AI工具)无需声明。在任何情况下,作者都必须对文本的最终版本负责。
关键词 AI署名权 大型语言模型 LLMs DeepSeek 作者署名 ChatGPT
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
8
《上海口腔医学》 CAS CSCD 2026年第1期6-6,共1页
投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨... 投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨慎。任何AI工具生成的文本、图表,不能在论文中使用。 展开更多
关键词 AIGC工具 LLMs ChatGPT 投稿论文 原创 大型语言模型
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
9
《中国口腔颌面外科杂志》 CAS 2026年第1期39-39,共1页
投稿论文必须为原创,任何大型语言模型工具(例如Chat GPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用Chat GPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须... 投稿论文必须为原创,任何大型语言模型工具(例如Chat GPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用Chat GPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨慎。任何AI工具生成的文本、图表,不能在论文中使用。 展开更多
关键词 Chat GPT 抄袭 LLMs 版权 致谢 原创
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
10
《中国口腔颌面外科杂志》 CAS 2026年第4期395-395,共1页
AI署名权:LLMs,如ChatGPT、DeepSeek等,目前不符合作者署名标准,应在稿件的“方法”部分妥善标识LLM的使用,用于“AI辅助文稿编辑”目的的LLM(或其他AI工具)无需声明。在任何情况下,作者都必须对文本的最终版本负责。
关键词 AI署名权 大型语言模型 LLMs DeepSeek 作者署名 ChatGPT
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
11
《上海口腔医学》 CAS CSCD 2026年第2期191-191,共1页
投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨... 投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨慎。任何AI工具生成的文本、图表,不能在论文中使用。 展开更多
关键词 AIGC工具 LLMs ChatGPT 投稿论文 原创 大型语言模型
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
12
《上海口腔医学》 CAS CSCD 2026年第3期324-324,共1页
投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨... 投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨慎。任何AI工具生成的文本、图表,不能在论文中使用。 展开更多
关键词 AIGC工具 LLMs ChatGPT 投稿论文 原创 大型语言模型
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
13
《中国口腔颌面外科杂志》 CAS 2026年第3期271-271,共1页
投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨... 投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨慎。任何AI工具生成的文本、图表,不能在论文中使用。 展开更多
关键词 AIGC工具 LLMs ChatGPT 投稿论文 原创 大型语言模型
暂未订购 下载PDF
本刊关于使用大型语言模型(large language models,LLMs)工具的规定 认领 引用
14
《中国口腔颌面外科杂志》 CAS 2026年第2期208-208,共1页
投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨... 投稿论文必须为原创,任何大型语言模型工具(例如ChatGPT)不能列为论文作者。如在论文创作中使用过相关工具,应在“方法”或“致谢”或适当的部分明确说明。使用ChatGPT等AIGC工具辅助完成论文撰写,可能涉及抄袭及版权问题,使用者必须谨慎。任何AI工具生成的文本、图表,不能在论文中使用。 展开更多
关键词 AIGC工具 LLMs ChatGPT 投稿论文 原创 大型语言模型
暂未订购 下载PDF
PrivLLM-Guard: A Differentially-Private Large Language Model for Real-Time Confidential Medical Text Generation and Summarization 认领 引用
15
作者 Ans D.Alghamdi 《Computers, Materials & Continua》 SCIE EI 2026年第6期1687-1727,共41页
How can AI assist doctors in generating clinical reports without compromising patient privacy?This question motivates our development of PrivLLM-Guard,a novel framework for differentially private large language models... How can AI assist doctors in generating clinical reports without compromising patient privacy?This question motivates our development of PrivLLM-Guard,a novel framework for differentially private large language models(LLMs)tailored to real-time confidential medical text generation and summarization.While LLMs have shown promise in automating clinical documentation,the sensitivity of healthcare data demands rigorous privacy protections.PrivLLM-Guard addresses this need by combining advanced—differential privacy techniques with adaptive noise calibration,ensuring robust privacy guarantees without sacrificing utility.The framework integrates bidirectional transformer encoders with autoregressive decoders,further enhanced by privacy-aware attention and gradient perturbation mechanisms.Extensive experiments on three large-scale medical datasets demonstrate BLEU-4 scores of 89.7%for generation and ROUGE-L scores of 92.3%for summarization,while maintaining strict privacy budgets.The model processes 512-token sequences in real time with an average latency of 245 ms and memory usage of just 4.2 GB.Compared to state-of-the-art privacy-preserving LLMs,PrivLLM-Guard improves the utility-privacy trade-off by 15.8%and reduces computational overhead by 23.4%.Key contributions include adaptive noise injection,dynamic privacy budgeting,and an integrated privacy auditing module—collectively advancing secure and trustworthy AI deployment in clinical environments. 展开更多
关键词 Differential privacy large language models medical text generation privacy-preserving computing healthcare AI text summarization real-time processing
暂未订购 下载PDF
Knowledge-Empowered,Collaborative,and Co-Evolving AI Models:The Post-LLM Roadmap 认领 引用 被引量：8
16
作者 Fei Wu Tao Shen +17 位作者 Thomas Back Jingyuan Chen Gang Huang Yaochu Jin Kun Kuang Mengze Li Cewu Lu Jiaxu Miao Yongwei Wang Ying Wei Fan Wu Junchi Yan Hongxia Yang Yi Yang Shengyu Zhang Zhou Zhao Yueting Zhuang Yunhe Pan 《Engineering》 SCIE EI CSCD 2025年第1期87-100,共14页
Large language models(LLMs)have significantly advanced artificial intelligence(AI)by excelling in tasks such as understanding,generation,and reasoning across multiple modalities.Despite these achievements,LLMs have in... Large language models(LLMs)have significantly advanced artificial intelligence(AI)by excelling in tasks such as understanding,generation,and reasoning across multiple modalities.Despite these achievements,LLMs have inherent limitations including outdated information,hallucinations,inefficiency,lack of interpretability,and challenges in domain-specific accuracy.To address these issues,this survey explores three promising directions in the post-LLM era:knowledge empowerment,model collaboration,and model co-evolution.First,we examine methods of integrating external knowledge into LLMs to enhance factual accuracy,reasoning capabilities,and interpretability,including incorporating knowledge into training objectives,instruction tuning,retrieval-augmented inference,and knowledge prompting.Second,we discuss model collaboration strategies that leverage the complementary strengths of LLMs and smaller models to improve efficiency and domain-specific performance through techniques such as model merging,functional model collaboration,and knowledge injection.Third,we delve into model co-evolution,in which multiple models collaboratively evolve by sharing knowledge,parameters,and learning strategies to adapt to dynamic environments and tasks,thereby enhancing their adaptability and continual learning.We illustrate how the integration of these techniques advances AI capabilities in science,engineering,and society—particularly in hypothesis development,problem formulation,problem-solving,and interpretability across various domains.We conclude by outlining future pathways for further advancement and applications. 展开更多
关键词 Artificial intelligence Large language models Knowledge empowerment Model collaboration Model co-evolution
暂未订购 下载PDF
基于大语言模型(LLMs)的地质灾害风险防控体系建设 认领 引用 被引量：4
17
作者 张茂省 郭柱国 +7 位作者 闫雨藤 郭迟辉 杨传波 冯立 孙萍萍 贾俊 董英 刘锋 《中国地质》 CAS CSCD 北大核心 2026年第1期136-157,共22页
【研究目的】在全球气候变化与人类活动日趋剧烈的背景下,地质灾害愈发呈现出突发、多发、复杂等特征,对现有地质灾害风险防控体系的应对能力提出了新的挑战,亟需探索新时期地质灾害风险管理的智能化路径。【研究方法】本文系统回顾了... 【研究目的】在全球气候变化与人类活动日趋剧烈的背景下,地质灾害愈发呈现出突发、多发、复杂等特征,对现有地质灾害风险防控体系的应对能力提出了新的挑战,亟需探索新时期地质灾害风险管理的智能化路径。【研究方法】本文系统回顾了近年来国内外地质灾害风险防控领域的研究进展,聚焦中国传统防控体系在风险识别、评估与管控环节面临的突出瓶颈,探讨了其技术赋能的发展过程。在此基础上,提出引入大语言模型(Large Language Models,LLMs)作为核心支撑的智能化地质灾害风险防控框架。【研究结果】本研究设计了一个基于LLMs的地质灾害风险防控体系,贯穿“智能识别-动态评估-协同管理”的全过程,推动地质灾害风险防控向智慧化、系统化方向转型。【结论】通过大语言模型与地质灾害防控场景的深度融合,有望为实现地质灾害防治现代化提供智能化的系统性解决方案。 展开更多
关键词 大语言模型(LLMs) 地质灾害 风险防控体系 人工智能 智能防灾减灾 地质灾害调查工程
暂未订购 下载PDF
基于LLM增强主题分析与主体建模的国产大模型舆情动态演化模拟 认领 引用 被引量：4
18
作者 张凯航 董昌其 +1 位作者 于光 郭毅峰 《情报杂志》 CSSCI 北大核心 2026年第1期99-109,共11页
[目的]通过整合语义分析与多主体建模,构建国产大模型舆情动态演化的预测框架,揭示舆情形成的深层机制及发展轨迹。[方法]以DeepSeek国产大模型舆情为研究对象,采用LLM增强的BERTopic方法对约25万条社交媒体数据进行主题分析与情感识别... [目的]通过整合语义分析与多主体建模,构建国产大模型舆情动态演化的预测框架,揭示舆情形成的深层机制及发展轨迹。[方法]以DeepSeek国产大模型舆情为研究对象,采用LLM增强的BERTopic方法对约25万条社交媒体数据进行主题分析与情感识别,提取舆情特征并构建Agent-Based建模系统,模拟不同用户群体在耦合网络环境下的参与模式、情感动态与网络演化过程。[结果/结论]研究表明,DeepSeek舆情具有三个显著特征:情感波动对微博数量变化具有预测作用,热度下降期仍保持正向情绪主导,争议主要围绕具体事件而非技术本身。不同用户群体展现差异化关注点与情感表达模式,普通用户对技术竞争框架情感投入最高;网络结构在舆情演进中由随机连接向无标度分布转变,形成意见领袖主导的舆论格局。研究结果为国产技术舆情动态监测与引导提供了方法论支持,对推动国产大模型等新兴技术的社会认知形成具有实践价值。 展开更多
关键词 国产大模型 网络舆情 舆情演化模拟 LLM增强主题分析 主体建模 DeepSeek
暂未订购 下载PDF
融合LLM-RAG-KG的电力生产安全事故问答大模型 认领 引用 被引量：1
19
作者 晋良海 张倩 +2 位作者 徐童欣 陈云 彭仲文 《中国安全科学学报》 EI CAS CSCD 北大核心 2026年第3期66-73,共8页
为解决传统分析方法在面对电力系统多因素非线性交互的复杂特性时存在专业知识整合不足、因果推理可解释性弱等固有局限,提出一种融合大型语言模型(LLM)、检索增强生成(RAG)和知识图谱(KG)的电力生产安全事故分析大模型;构建包含知识检... 为解决传统分析方法在面对电力系统多因素非线性交互的复杂特性时存在专业知识整合不足、因果推理可解释性弱等固有局限,提出一种融合大型语言模型(LLM)、检索增强生成(RAG)和知识图谱(KG)的电力生产安全事故分析大模型;构建包含知识检索、知识推理、答案生成与效果评估4个核心模块框架:基于RAG技术从专业文本中精准检索相关知识,利用KG结构化推理事故实体和关系,以弥补检索盲区;通过LLM生成专业、可解释的事故因果分析答案,通过主观专家评分与自动评估指标(ROUGE)、双语替换学习(BLEU)等客观指标全面评估系统。结果表明:在电力生产安全事故分析场景中,RAG与KG的知识增强技术对具备一定规模参数的基础模型有普适性性能提升,能帮助模型精准捕捉设备故障传导链等专业关联,提升事故致因挖掘与结果演化推理质量;DeepSeek-R1、Qwen2.5-72B等大模型在该模式下解析专业术语、梳理多因素关联的准确性显著提高,其中DeepSeek-R1综合评分达4.05分,更满足领域精度要求;增强效果存在模型能力阈值,Qwen2.5-72B增强后能高效解析跨区域电网故障联动等复杂逻辑,且平衡性能与部署成本,适配企业实际需求,而Qwen2.5-14B等小模型因基础推理能力有限,引入外部知识后难处理专业信息,性能下降,无法满足专业性要求。 展开更多
关键词 大型语言模型(LLM) 检索增强生成(RAG) 知识图谱(KG) 电力生产安全事故 事故分析 DeepSeek-R1
暂未订购 下载PDF
基于“LLM+Agent”的在轨服务自主任务规划技术 认领 引用 被引量：1
20
作者 李胤慷 王浩 +4 位作者 袁容昊 王阳阳 刘晓坤 唐生勇 李爽 《上海航天（中英文）》 CSCD 2026年第1期169-179,共11页
针对传统在轨服务任务规划中“人在回路”模式存在的决策链条冗长、人工干预依赖度高等瓶颈问题,本文提出一种基于“LLM+Agent”的自主任务规划方法。首先,构建了基于“LLM+Agent”的智能体决策架构,实现大模型语义理解与算法工具集精... 针对传统在轨服务任务规划中“人在回路”模式存在的决策链条冗长、人工干预依赖度高等瓶颈问题,本文提出一种基于“LLM+Agent”的自主任务规划方法。首先,构建了基于“LLM+Agent”的智能体决策架构,实现大模型语义理解与算法工具集精确计算的深度协同;在此基础上,设计了基于模型上下文协议(MCP)的异构模型交互框架,实现大模型异构算法工具间的高效数据流转与系统的灵活拓展;随后,基于在轨服务通用任务规划算法,建立了标准化MCP服务算法工具集,并设计面向空间在轨服务任务语义的提示模板,从而提升大模型规划可靠性;最后,通过从任务指令解析到执行反馈的闭环测试,验证了所提出的技术能够实现在轨服务自主任务规划,并提高任务决策效率。 展开更多
关键词 在轨服务 任务规划 大模型(LLM) 自主决策
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 250 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈