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92,173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：
Domain-Specific Large Language Model for Maintenance Decision-Making on Wind Farms by Labeled-Data-Supervised Fine-Tuning 认领 引用 被引量：1
1
作者 Dongming Fan Meng Liu +5 位作者 Yi Shao Linchao Yang Yiliu Liu Yue Zhang Yi Ren Zili Wang 《Engineering》 SCIE EI CSCD 2026年第5期343-361,共19页
Wind farm operators always need a better maintenance strategy to increase resource utilization efficiency while controlling operation and maintenance costs.However,conventional maintenance decision-making approaches a... Wind farm operators always need a better maintenance strategy to increase resource utilization efficiency while controlling operation and maintenance costs.However,conventional maintenance decision-making approaches are time-consuming and have poor flexibility and adaptability to various scenarios.This study addressed these challenges by using a large language model(LLM)to understand,generate,and plan maintenance strategies for wind farms characterized by various failure modes and maintenance costs.A labelled-data-supervised fine-tuning LLM for maintenance,named LLM4M,is proposed.The proposed LLM4M model is trained on an extensive dataset of mathematical programs for maintenance to generate optimal strategies for wind farms.Compared with other large parameter LLMs,the fine-tuned LLM4M model demonstrates remarkable accuracy,with an error of approximately 2%from the optimal strategy.In addition,the generalization of the proposed LLM4M model has achieved remarkable results.If the LLM4M model correctly generates the maintenance strategy,the maintenance cost deviates from the optimal solution by only approximately 5%.Furthermore,phase transition behavior is observed,which provides considerable guidance for the development of domain-specific LLMs for the maintenance domain. 展开更多
关键词 Large language model Maintenance decision-making Wind farms Fine-tuning
暂未订购 下载PDF
Agentic Robotic Boxes for Perovskite Solar Cell Fabrication with Recipe Language Model 认领 引用
2
作者 Zijian Chen Wenjin Yu +22 位作者 Chuang Wu Feibei Chen Zixuan Wang Chao Zhou Yimeng You Shaojie Li Qiyuan Zhu Ning Ma Yao Sun Donghui Li Billy Fanady Shengchou Jiang Zhongliang Yan Shumin Zhou Liang Li Chang-Yu Hsieh Yang Bai Lixin Xiao Chi-yung Chung Ching-chuen Chan Zhanfeng Cui Michael Grätzel Haitao Zhao 《Engineering》 SCIE EI CSCD 2026年第6期365-374,共10页
Perovskite solar cells(PSCs)have been undergoing rapid development with the vast combinatorial explo-ration of recipes;however,the related research suffers from time-consuming trial-and-error synthesis and labor-inten... Perovskite solar cells(PSCs)have been undergoing rapid development with the vast combinatorial explo-ration of recipes;however,the related research suffers from time-consuming trial-and-error synthesis and labor-intensive fabrication.As a promising alternative,interconnected robotic boxes that integrate fabrication and characterization enable high-throughput experimentation and data collection;however,the resulting numerical datasets are often insufficiently analyzed and fail to provide effective feedback for semantic recipe optimization.Here,we conceived and realized an emerging scientific tool of robotic boxes enabled by a domain-specific recipe language model(RLM)and a coordinating language agent for PSCs research.The developed agent features two loops of seven artificial intelligence(AI)layers,in which both numerical and semantic recipes were continuously learned and optimized from the literature and robotic corpora for iterative fine-tuning of the RLM.Guided by the agent,11 robotic boxes executed the controllable synthesis,fabrication,and characterization of 50764 PSCs,increasing the power conver-sion efficiency(PCE)to 27.0%(26.5%certified).Simultaneously,more than 578 million tokens were gen-erated and augmented to improve the ability to recommend a recipe and mechanistic reasoning,achieving an overall score of about 80%based on the dedicated evaluation criteria.Thus,such agentic robotic boxes provide an advanced tool for the next-generation synthesis,fabrication,characterization,and even mechanistic reasoning of PSCs and beyond. 展开更多
关键词 Robotics Language agent Recipe language model Materials intelligence Perovskite solar cells Device fabrication
暂未订购 下载PDF
Development of a large language model-driven intelligent agent for predicting relative permeability in oil and gas reservoirs 认领 引用
3
作者 Jiulong Wang Yuanchun Zhou +2 位作者 Xuhui Zhang Junming Lao Hongqing Song 《Theoretical & Applied Mechanics Letters》 EI CAS CSCD 2026年第3期91-98,共8页
To address the challenges and difficulties in predicting the relative permeability of reservoirs using traditional physics-driven and data-driven approaches,this paper proposes a collaborative analysis intelligent age... To address the challenges and difficulties in predicting the relative permeability of reservoirs using traditional physics-driven and data-driven approaches,this paper proposes a collaborative analysis intelligent agent for the relative permeability of oil and gas reservoirs based on a large model.By constructing a multiagent collaborative workflow,integrated collaboration of data,models,and analysis results is achieved.The intelligent agent automatically completes data preprocessing,feature extraction,parameter calibration,small model calling,and output and evaluation of prediction results based on preset task dependencies.At the same time,by introducing deep learning-based embedding of physical information,the analysis efficiency and accuracy are significantly improved.The results show that compared with traditional physical analysis methods,this method improves the accuracy of reservoir relative permeability prediction by 10%,has a computational efficiency 10 times higher than traditional deep learning algorithms,and a computational speed 100–1,000 times higher than conventional physical models.This study further enhances the efficiency and intelligence of physical property analysis of oil and gas reservoirs,providing a new research direction for the intelligent development of oil and gas digitization. 展开更多
关键词 Relative permeability Large language model Intelligent agent
暂未订购 下载PDF
Large Language Model-Enabled Constitutive Modeling for Rate-Dependent Plasticity and Automatic UMAT Subroutine Generation 认领 引用
4
作者 Yuchuan Gu Lusheng Wang +3 位作者 Jun Ding Yanhong Peng Changgeng Li Shaojie Gu 《Computers, Materials & Continua》 SCIE EI 2026年第5期315-329,共15页
In materials science and engineering design,high-fidelity and high-efficiency numerical simulation has become a driving force for innovation and practical implementation.To address longstanding bottlenecks in the deve... In materials science and engineering design,high-fidelity and high-efficiency numerical simulation has become a driving force for innovation and practical implementation.To address longstanding bottlenecks in the development of conventional material constitutive models—such as lengthy modeling cycles and difficulties in numerical implementation—this study proposes an intelligent modeling and code generation approach powered by large languagemodels.A structured knowledge base integrating constitutive theory,numerical algorithms,and UMAT(User Material)interface specifications is constructed,and a retrieval-augmented generation strategy is employed to establish an end-to-end workflow spanning experimental data parsing,constitutive model formulation,and automatic UMAT subroutine generation.Experimental results show that the method achieves high accuracy for both a classical Johnson–Cookmodel and a physics-informed neural network(PINN)model,with key parameter identification errors below 5%.Moreover,the automatically generated UMAT subroutines yield finite element simulation results in Abaqus that are highly consistent with theoretical predictions(coefficient of determination R2>0.98)while maintaining good numerical stability.This framework is currently focused on the automatic construction of rate-dependent elastoplastic material models,and its core method also provides a clear path for extending to other constitutive categories such as hyperelasticity and viscoelasticity.This work provides an effective technical route for the rapid development and reliable numerical implementation of material constitutive models,significantly advancing the intelligence level of computational mechanics research and improving engineering application efficiency. 展开更多
关键词 Large language model constitutive model UMAT subroutine
暂未订购 下载PDF
Bilingual evaluation of large language models for patient education in refractive surgery 认领 引用
5
作者 Tsung-Hsien Tsai Chin-Ling Tsai +2 位作者 Jui-Hung Hsu Ching-Hsi Hsiao Hung-Chi Chen 《International Journal of Ophthalmology(English edition)》 SCIE CAS 2026年第6期1019-1027,共9页
AIM:To evaluate the ability of six advanced large language models(LLMs)—in providing accurate,comprehensive,and readable patient education on corneal refractive surgeries[laser in-situ keratomileusis(LASIK),keratoref... AIM:To evaluate the ability of six advanced large language models(LLMs)—in providing accurate,comprehensive,and readable patient education on corneal refractive surgeries[laser in-situ keratomileusis(LASIK),keratorefractive lenticule extraction(KLEx),and photorefractive keratectomy(PRK)]in both English and Chinese.METHODS:This is a cross-sectional,comparative study.Twenty-six questions,compiled from authoritative ophthalmologic sources and covering four domains(procedure basics and eligibility;safety,risks and longterm stability;recovery and postoperative experience;and practical concerns),were administered in both English and Chinese via fresh chat sessions with each LLM,respectively.Five performance metrics were evaluated:accuracy,comprehensiveness,word count,readability,and reproducibility,using appropriate statistical tests.RESULTS:OpenAI o1 and DeepSeek-R1 consistently achieved the highest accuracy and most comprehensive responses,significantly outperforming ChatGPT-4o,Gemini Advanced,Claude Sonnet,and Tongyi Qwen(Friedman P<0.001).Although overall accuracy and comprehensiveness were similar across languages,Chinese responses were significantly longer.Readability varied among the models,with Claude Sonnet generally producing the most readable English texts.Reproducibility analysis revealed moderate consistency,reflecting inherent variability in outputs to identical prompts.CONCLUSION:Reasoning-augmented LLMs,particularly OpenAI o1 and DeepSeek-R1,demonstrate superior performance in delivering bilingual patient education for corneal refractive surgery,with high accuracy and comprehensiveness.However,variations in response length,readability,and reproducibility indicate that further refinement is necessary before these tools can be reliably integrated into clinical practice. 展开更多
关键词 large language models refractive surgery patient education
暂未订购 下载PDF
Towards Generalisable and Explainable Traffic Signal Control via Deep Reinforcement Learning and Large Language Models 认领 引用
6
作者 Hao Huang Wenjie He +6 位作者 Qilie Liu Qian Liu Chao Huang Anwar PPAbdul Majeed Xiangguang Dai Gang Fang Xiaohua Xu 《CAAI Transactions on Intelligence Technology》 SCIE EI CSCD 2026年第2期483-497,共15页
As a government-regulated public service,traffic signal control(TSC)requires reliable and transparent decision-making.However,existing deep reinforcement learning(DRL)methods,despite improvements in control accuracy,s... As a government-regulated public service,traffic signal control(TSC)requires reliable and transparent decision-making.However,existing deep reinforcement learning(DRL)methods,despite improvements in control accuracy,still lack explainability and generalisation,severely limiting their applicability in real-world environments.To address the challenges above,this paper proposes GenEx-TSC,a generalisable and explainable TSC method that integrates deep reinforcement learning with large language models(LLMs).First,starting from vehicle-level states,we train a DRL agent incorporating intersection physical heterogeneity and neighbourhood information,which lays the evaluation foundation for constructing a high-quality LLM dataset.Subsequently,the LLM agent is optimised through a two-stage training mechanism.In the distillation stage,a lightweight LLM agent is trained using the reasoning trajectories of a larger-scale LLM agent,inheriting its semantic understanding and decision-generation capabilities and in the alignment stage,the DRL evaluation network is employed to calibrate the outputs of the distilled LLM agent,ensuring that the generated cycle-level signal timing strategies are both efficient and interpretable.We synthesise 10 intersection networks with different physical attributes in SUMO and set traffic flows of varying scales.Experimental results across diverse traffic environments demonstrate that the proposed GenEx-TSC exhibits clear advantages over traditional methods,mainstream DRL methods and LLM baselines in terms of control accuracy,generalisation and explainability. 展开更多
关键词 deep reinforcement learning explainable intelligence large language model traffic signal control
暂未订购 下载PDF
ZhongdaChat-ED:a medical large language model for personalized erectile dysfunction health consultation and professional clinical decision-making using retrieval-augmented generation 认领 引用
7
作者 Yi Xia Yong-Kun Zhu +6 位作者 Chun-Hui Liu Xiang Hong Rui-Xin Zhang Nie-Ke Zhang Ming Chen Guang-Yuan Zhang Chao Sun 《Asian Journal of Andrology》 SCIE CAS CSCD 2026年第1期71-79,共9页
Artificial intelligence(AI)-driven large language models(LLMs)hold potential for medical applications but face challenges,such as inaccurate or outdated training data.In this study,ZhongdaChat-ED,a personalized medica... Artificial intelligence(AI)-driven large language models(LLMs)hold potential for medical applications but face challenges,such as inaccurate or outdated training data.In this study,ZhongdaChat-ED,a personalized medical LLM integrating retrieval-augmented generation(RAG)technology,was developed to enhance erectile dysfunction(ED)counseling and clinical decision-making.The model was built using the open-source Deepseek-r1:32b framework,augmented with two specialized databases:a patient health consultation database and a clinical decision support database updated with real-time medical advancements.Two versions of ZhongdaChat-ED were developed:a Consumer Version for patient-facing health consultations and a Professional Version for clinician support.Performance was evaluated against four commonly used LLMs(ChatGPT4,Copilot,Claude,and Gemini)through simulated clinical consultations and case analyses.Three urologists and three patients assessed responses across various dimensions,including accuracy,human caring,ease of understanding,clinical significance,and informational frontier.The Consumer Version outperformed commonly used LLMs in accuracy(4.77/5),human caring(4.86/5),and ease of understanding(4.88/5)with all P85.2%case score rate)and informational frontier scores(4.52/5)than those of other models(P<0.001).ZhongdaChat-ED effectively addresses limitations of conventional LLMs by leveraging RAG to integrate real-time,domain-specific data.ZhongdaChat-ED shows promise in enhancing patient health consultation and clinician decision-making for ED,underscoring the value of tailored AI systems in bridging gaps between generalized AI and specialized medical needs.Future work should expand multimodal capabilities and cross-disciplinary integration to broaden clinical utility. 展开更多
关键词 artificial intelligence clinical decision-making erectile dysfunction large language models medical consultation ZhongdaChat-ED
暂未订购 下载PDF
ComAlign:A Benchmark Aligning Natural Language with Operating System Commands 认领 引用
8
作者 Shasha Li Bin Ji +2 位作者 Xiaodong Liu Jun Ma Jie Yu 《Computers, Materials & Continua》 SCIE EI 2026年第5期1255-1271,共17页
Aligning natural language with operating system(OS)commands allows users to performcomplex computer tasks through simple natural language descriptions.However,due to the complex nature of natural language,it still rem... Aligning natural language with operating system(OS)commands allows users to performcomplex computer tasks through simple natural language descriptions.However,due to the complex nature of natural language,it still remains challenging to achieve precise alignment.In this paper,we present ComAlign,a Chinese benchmark dataset that pairs Chinese natural language descriptions with corresponding OS commands.ComAlign covers a broad range of 82 distinct OS command types with a total of 1811 natural language descriptions.We elaborate on the construction of ComAlign and construct three baselines to evaluate the alignment accuracy on ComAlign.Experimental results show that even advanced large language models struggle with certain ambiguously phrased OS commands.Specifically,the best performing baseline achieves 46.9%alignment accuracy.We demonstrate that ComAlign is collected from realworld application scenarios,making it particularly suitable for developing and benchmarking intelligent OS and agent systems that support user-machine interactions through natural language. 展开更多
关键词 Large language model language-command alignment artificial intelligence operating system
暂未订购 下载PDF
Q&A system for international construction contracts driven by large language model and knowledge graph 认领 引用
9
作者 Yongcheng FU Tong LYU +1 位作者 Yongqiang CHEN Ziyun LV 《ENGINEERING Management》 CSCD 2026年第1期124-145,共22页
As international construction projects continue to expand,construction enterprises are accumulating vast amounts of contract‑related text data,making the effective management and extraction of knowledge from these den... As international construction projects continue to expand,construction enterprises are accumulating vast amounts of contract‑related text data,making the effective management and extraction of knowledge from these dense texts essential to mitigate knowledge loss and ensure efficient contract management.The advent of large language models(LLMs)presents a promising avenue for enhancing contract knowledge management through intelligent systems.However,challenges such as hallucination,inflexibility,and lack of interpretability often diminish practitioners’confidence in applying these models to real‑world scenarios.This study seeks to develop a knowledge‑based question‑and‑answer(Q&A)system for international construction contracts by integrating both the knowledge graph(KG)and the LLM.Built upon a domain‑specific KG derived from the 2022 edition of the Fédération Internationale des Ingénieurs‑Conseils(FIDIC)Yellow Book and the NEC4 Conditions of Contract,the system leverages LLM to conduct synergistic reasoning with the KG,enabling it to answer complex queries using both tacit knowledge and external sources.Experimental results demonstrate that the proposed approach markedly enhances the model’s performance in Q&A tasks of contract knowledge,achieving an average success rate exceeding 87%in terms of both accuracy and interpretability.This model provides a specialized Q&A system for international construction enterprises,facilitating flexible knowledge acquisition and task‑oriented analysis in contract management,while also introducing a novel framework for integrating AI technologies into the management of international construction contracts. 展开更多
关键词 international construction contract knowledge graph large language model knowledge management
暂未订购 下载PDF
Vision-Language Model-Based Human-Guided Mobile Robot Navigation in an Unstructured Environment for Human-Centric Smart Manufacturing 认领 引用
10
作者 Tian Wang Junming Fan +2 位作者 Pai Zheng Ruqiang Yan Lihui Wang 《Engineering》 SCIE EI CSCD 2026年第7期229-239,共11页
In smart manufacturing, autonomous mobile robots play an indispensable role in conducting inspection and material handling operations, yet they face significant limitations regarding adaptability and resilience within... In smart manufacturing, autonomous mobile robots play an indispensable role in conducting inspection and material handling operations, yet they face significant limitations regarding adaptability and resilience within unstructured environments. Vision and language navigation (VLN), a human-guided navigation paradigm, emerges as a compelling solution to these challenges. Nevertheless, VLN’s practical implementation is constrained by limited task generalization capabilities, inadequate response to diverse linguistic commands, and insufficient consideration of sensor-induced noise in environmental perception. This research addresses these limitations by introducing an innovative vision-language model (VLM)-based human-guided mobile robot navigation approach in an unstructured environment for human-centric smart manufacturing (HSM). This approach encompasses three-dimensional (3D) robust scene reconstruction through advanced point cloud techniques, zero-shot semantic segmentation via a VLM, and natural language processing through a large language model (LLM) to interpret instructions and generate control code for navigation. The system’s efficacy is validated through extensive experiments in an unstructured manufacturing setup. 展开更多
关键词 Vision-language model Large language model Human-robot interaction Mobile robot navigation Human-centric smart manufacturing
暂未订购 下载PDF
Multitype Game Optimisation:A Two-Stage Fine-Tuning Framework for Multi-Game Optimisation With Large Language Models 认领 引用
11
作者 Xiali Li Jingshi Gu +3 位作者 Feifan He Yang Xiao Yuanli Jia Ping Lan 《CAAI Transactions on Intelligence Technology》 SCIE EI CSCD 2026年第3期739-753,共15页
Large language models(LLMs)have made remarkable advances in natural language processing,demonstrating great potential in modelling structured sequences.However,adapting these capabilities to machine gaming tasks such ... Large language models(LLMs)have made remarkable advances in natural language processing,demonstrating great potential in modelling structured sequences.However,adapting these capabilities to machine gaming tasks such as Go remains challenging due to limitations in strategy generalisation and optimisation efficiency.This paper presents multitype game optimisation(MyGO),a two-stage fine-tuning framework tailored for two-player perfect information board games,exploring the applicability of LLMs to nonlinguistic decision-making domains.In the supervised fine-tuning stage,we propose a unified structural encoding method,action semantic unit(ASU),which efficiently converts heterogeneous game records into discrete token sequences compatible with LLMs.In the reinforcement learning stage,we design TA-PPO(token-level adaptive proximal policy optimisation),an enhanced PPO-based algorithm to address the issue of sparse feedback commonly encountered in game reinforcement learning.Experimental results demonstrate that the fine-tuned models achieve superior or comparable performance to traditional game-playing algorithms in terms of strategy quality,rule generalisation and inference efficiency.This work provides a scalable paradigm for fine-tuning LLMs in complex decision-making tasks and lays a foundation for future research in game AI and generalisable strategy optimisation. 展开更多
关键词 computer game fine‐tuning large language models reinforcement learning reward function
暂未订购 下载PDF
A Metaheuristic Football Optimization Algorithm Integrated with Large Language Models for Automated Seismic Time-Series Modeling 认领 引用
12
作者 Amal H.Alharbi Marwa M.Eid +2 位作者 Nima Khodadadi Ebrahim A.Mattar Sayed Elkenawy 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第5期947-987,共41页
Seismic time series forecasting remains challenging due to the nonlinearity,non-stationarity,and noise of earthquake data,and because deep learning models are sensitive to preprocessing and hyperparameter settings.Alt... Seismic time series forecasting remains challenging due to the nonlinearity,non-stationarity,and noise of earthquake data,and because deep learning models are sensitive to preprocessing and hyperparameter settings.Although recent studies have improved neural architectures and optimization techniques,preprocessing is often treated as a fixed or manually designed stage,with limited integration into model optimization.To address this,this paper proposes an integrated,data-driven modelling framework that combines guided preprocessing with systematic hyperparameter optimization for seismic prediction,specifically forecasting earthquake magnitude from seismic catalog time-series data,with experiments conducted on Canadian seismic records.The method uses a Large Language Model to guide data preparation and feature engineering,rather than fully automate them,and applies deep learning-based forecasting with the N-HITS architecture,optimized via metaheuristic-assisted feature selection and hyperparameter tuning.The Football Optimization Algorithm(FbOA),employed as a metaheuristic optimization strategy in this study,is evaluated and compared with several well-known optimizers under identical conditions.The results show significant performance gains,with FbOA achieving superior accuracy,robustness,and convergence compared to baseline and competing methods.Notably,error metrics are reduced(MSE 3.10×10-7,RMSE 5.57×103),with high performance indicators(r=0.982,R2=0.979,NSE=0.981,WI=0.985).These results highlight the value of integrating guided preprocessing with optimization and demonstrate a scalable framework for high-precision time-series prediction in geophysical and related domains. 展开更多
关键词 Seismic time-series forecasting large language models metaheuristic algorithms football optimization algorithm earthquake modeling
暂未订购 下载PDF
Diversified Composite Prompting to Enhance Generalisation of Vision-Language Models 认领 引用
13
作者 Xiaoyong Mei Chong Tang +3 位作者 Zhengqun Dai Fudan Zheng Kongwen Zhang Tianyu Lin 《CAAI Transactions on Intelligence Technology》 SCIE EI CSCD 2026年第3期935-950,共16页
In recent years,prompt learning has shown promise in transferring pretrained vision-language models(VLMs)to downstream tasks.However,existing methods face two challenges in improving generalisation:(1)When leveraging ... In recent years,prompt learning has shown promise in transferring pretrained vision-language models(VLMs)to downstream tasks.However,existing methods face two challenges in improving generalisation:(1)When leveraging the collaborative effect of multimodal prompts,it is often assumed that text and visual modalities share the same prompt requirements,neglecting the distinct hierarchical processing of their encoders,leading to prompt imbalance;and(2)current methods exhibit limited adaptability when facing diverse distribution shift scenarios,including class distribution shifts and image content variations.To address these challenges,we propose a diversified composite prompt learning(DCPL)framework that integrates unified and specific prompts.Specifically,to alleviate multimodal prompt imbalance,we design a shared root multimodal prompting strategy,which employs a shared root prompt and an independent derivation mechanism to generate the derived multimodal prompt(DMP),enabling independent deep prompting while maintaining implicit synergy across modalities.Furthermore,we design a dual-branch dynamic adaptive prompting strategy that produces the derived class-specific prompt(DCP)and imagespecific prompt(ISP),driven by inter-class relations and image-patch context,respectively,to enhance adaptability across different distribution shifts.Extensive experiments on base-to-novel,cross-dataset,domain generalisation and few-shot learning demonstrate that the DCPL achieves superior performance,validating its robustness and generalisation. 展开更多
关键词 domain generalisation few‐shot learning prompt learning transfer learning vision‐language model
暂未订购 下载PDF
Large Language Models for Cybersecurity Intelligence: A Systematic Review of Emerging Threats, Defensive Capabilities, and Security Evaluation Frameworks 认领 引用
14
作者 Hamed Alqahtani Gulshan Kumar 《Computers, Materials & Continua》 SCIE EI 2026年第6期297-367,共71页
Large Language Models(LLMs)are becoming integral components of modern cybersecurity ecosystems,simultaneously strengthening defensive capabilities while giving rise to a new class of Artificial Intelligence-Generated ... Large Language Models(LLMs)are becoming integral components of modern cybersecurity ecosystems,simultaneously strengthening defensive capabilities while giving rise to a new class of Artificial Intelligence-Generated Content(AIGC)-driven threats.This PRISMA-guided systematic review synthesises 167 peer-reviewed studies published between 2022 and 2025 and proposes a unified threat-defence-evaluation taxonomy as a central analytical framework to consolidate a previously fragmented body of research.Guided by this taxonomy,the review first examines AIGC-enabled threats,including automated and highly personalised phishing,polymorphic malware and exploit generation,jailbreak and adversarial prompting,prompt-injection attack vectors,multimodal deception,persona-steering attacks,and large-scale disinformation campaigns.The surveyed evidence indicates a qualitative escalation in adversarial capabilities,with LLMs significantly enhancing scalability,adaptability,and realism while markedly reducing the technical barriers to conducting sophisticated attacks.Second,the review analyses LLM-enabled defensive applications spanning intrusion and anomaly detection,malware analysis and log-semantic modelling,multilingual threat intelligence extraction,vulnerability discovery and code repair,and Security Operations Center(SOC)automation through Retrieval-Augmented Generation(RAG)and multi-agent systems.Although these approaches demonstrate strong potential as semantic reasoning and decision-support components within hybrid security architectures,their real-world effectiveness remains constrained by hallucination risks,adversarial susceptibility,distributional shifts,and operational overhead.Third,the review synthesises current security evaluation and red-teaming practices,revealing a fragmented assessment landscape characterised by narrow benchmarks,inconsistent evaluation metrics,and limited longitudinal robustness analysis.Overall,the taxonomy-driven synthesis highlights a structurally imbalanced ecosystem in which offensive innovation outpaces defensive maturity and governance,and it informs a structured,research-question-aligned roadmap for developing trustworthy,resilient,and policy-aligned LLM-powered cybersecurity systems. 展开更多
关键词 Artificial intelligence-generated content threats cybersecurity intelligence large language model-based defensive systems large language models red-teaming and evaluation frameworks
暂未订购 下载PDF
Decision-making performance of large language models vs.human physicians in challenging lung cancer cases:A real-world case-based study 认领 引用
15
作者 Ning Yang Kailai Li +19 位作者 Baiyang Liu Xiting Chen Aimin Jiang Chang Qi Wenyi Gan Lingxuan Zhu Weiming Mou Dongqiang Zeng Mingjia Xiao Guangdi Chu Shengkun Peng Hank ZHWong Lin Zhang Hengguo Zhang Xinpei Deng Quan Cheng Bufu Tang Anqi Lin Juan Zhou Peng Luo 《Intelligent Oncology》 CAS 2026年第1期15-24,共10页
Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a fr... Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a framework for evaluating LLMs and physician decisions in challenging lung cancer cases.Methods:We curated 50 challenging lung cancer cases(25 local and 25 published)classified as complex,rare,or refractory.Blinded three-dimensional,five-point Likert evaluations(1–5 for comprehensiveness,specificity,and readability)compared standalone LLMs(DeepSeek R1,Claude 3.5,Gemini 1.5,and GPT-4o),physicians by experience level(junior,intermediate,and senior),and AI-assisted juniors;intergroup differences and augmentation effects were analyzed statistically.Results:Of 50 challenging cases(18 complex,17 rare,and 15 refractory)rated by three experts,DeepSeek R1 achieved scores of 3.95±0.33,3.71±0.53,and 4.26±0.18 for comprehensiveness,specificity,and readability,respectively,positioning it between intermediate(3.68,3.68,3.75)and senior(4.50,4.64,4.53)physicians.GPT-4o and Claude 3.5 reached intermediate physician–level comprehensiveness(3.76±0.39,3.60±0.39)but junior-to-intermediate physician–level specificity(3.39±0.39,3.39±0.49).All LLMs scored higher on rare cases than intermediate physicians but fell below junior physicians in refractory-case specificity.AIassisted junior physicians showed marked gains in rare cases,with comprehensiveness rising from 2.32 to 4.29(84.8%),specificity from 2.24 to 4.26(90.8%),and readability from 2.76 to 4.59(66.0%),while specificity declined by 3.2%(3.17 to 3.07)in refractory cases.Error analysis showed complementary strengths,with physicians demonstrating reasoning stability and LLMs excelling in knowledge updating and risk management.Conclusions:LLMs performed variably in clinical decision-making tasks depending on case type,performing better in rare cases and worse in refractory cases requiring longitudinal reasoning.Complementary strengths between LLMs and physicians support case-and task-tailored human–AI collaboration. 展开更多
关键词 Large language models Clinical evaluation Decision-making Lung cancer
暂未订购 下载PDF
Transfer learning with pre-trained language models for protein expression level prediction in Escherichia coli 认领 引用
16
作者 Chunhe Yang YuLing Zhao +3 位作者 Ruoyu Wang Haoran Li Xiaoping Liao Hongwu Ma 《Synthetic and Systems Biotechnology》 SCIE CSCD 2026年第2期115-123,共9页
Accurately predicting recombinant protein expression in Escherichia coli remains a long-standing challenge due to the multifactorial nature of gene regulation and translation.Existing computational approaches typicall... Accurately predicting recombinant protein expression in Escherichia coli remains a long-standing challenge due to the multifactorial nature of gene regulation and translation.Existing computational approaches typically emphasize either codon usage or protein sequence features,limiting predictive accuracy and generalizability.Here we present TLCP-EPE,a transfer learning framework that,for the first time,fuses codon-and protein-level pre-trained language models to jointly capture determinants of expression.By fine-tuning CaLM and ProtT5 with low-rank adaptation(LoRA)and integrating their embeddings through a BiGRU-MLP predictor,TLCP-EPE learns expression-aware representations that outperform state-of-the-art methods.Across two independent test datasets,TLCP-EPE achieved robust performance(AUC 0.835 on codon data;AUC 0.713 on protein data),consistently surpassing conventional codon-based metrics and deep learning baselines.Our results demonstrate that dual-modal modeling of codon and protein sequences enables more accurate and generalizable prediction of expression levels,providing a powerful foundation for rational protein design and biomanufacturing applications. 展开更多
关键词 Protein expression prediction Escherichia coli Transfer learning Pre-trained language model LoRA fine-tuning Fused sequence representations
Large language models for battery prognostics 认领 引用
17
作者 Jingyuan Zhao Yan Wang +2 位作者 Misheng Cai Lili Xie Hewu Wang 《Journal of Energy Chemistry》 SCIE EI CAS CSCD 2026年第4期159-177,I0006,共19页
Predicting battery health with accuracy and interpretability has become a grand challenge at the intersection of electrochemistry,artificial intelligence,and sustainable energy.Conventional data-driven and physics-bas... Predicting battery health with accuracy and interpretability has become a grand challenge at the intersection of electrochemistry,artificial intelligence,and sustainable energy.Conventional data-driven and physics-based methods remain constrained by nonlinear,coupled,and heterogeneous battery dynamics that limit generalization across chemistries,duty cycles,and environments.Recent breakthroughs in large language models(LLMs)and foundation-model artificial intelligence introduce a paradigm shift—enabling machines to learn from multimodal signals,encode physical laws,and reason adaptively across scales.This review unifies these advances into ten foundational methodologies that delineate the emerging landscape of intelligent battery prognostics:transfer learning,knowledge augmentation,physics-informed and explainable intelligence,ensemble fusion,causal reasoning,continual adaptation,multi-agent coordination,digital-twin coupling,and the pursuit of artificial general intelligence.Together,these dimensions redefine batteries from passive electrochemical devices into cognitive energy systems—self-optimizing,trustworthy,and responsive to uncertainty.Framed within the broader evolution toward Industry 5.0,we chart a roadmap for autonomous battery management that fuses physics,data,and reasoning,establishing artificial intelligence as a scientific and technological cornerstone for the next generation of resilient,adaptive,and sustainable electrification. 展开更多
关键词 Battery management system Artificial intelligence Deep learning Large language models Multi-agent Artificial general intelligence Industry 5.0
暂未订购 下载PDF
From evidence-based guidelines to practice:Using natural language processing to identify impactful interventions in falls prevention 认领 引用
18
作者 Shanoja Naik Hasitha Wimalarathna +1 位作者 Alexa Parousis Doris Grinspun 《International Journal of Nursing Sciences》 CSCD 2026年第3期299-306,I0003,I0004,共8页
Objectives This study aimed to identify and characterize implementation strategies for falls prevention in long-term care(LTC)homes using natural language processing(NLP)with a focus on the Registered Nurses’Associat... Objectives This study aimed to identify and characterize implementation strategies for falls prevention in long-term care(LTC)homes using natural language processing(NLP)with a focus on the Registered Nurses’Association of Ontario’s(RNAO)Preventing Falls and Reducing Injury from Falls(2017)Best Practice Guideline(BPG).Methods A retrospective quality improvement study was conducted using narrative reports submitted to RNAO MyBPSO reporting system from 63 Ontario LTC homes(2017 to 2022).Free-text data describing implementation activities were analyzed using an NLP pipeline that included text preprocessing,tokenization,and keyword extraction using Rapid Automatic Keyword Extraction(RAKE).Extracted terms were aggregated into candidate themes and further analyzed using a lexicon-informed sentiment analysis approach adapted for clinical language.Themes were iteratively refined through a structured consensus process involving multidisciplinary experts.Inter-rater agreement was assessed using Cohen’s kappa.Results A total of 153 reports generated 235 preliminary themes,which were refined through sentiment analysis and expert consensus into 10 themes.Commonly identified strategies included falls risk assessment,fall prevention strategies,risk factors of falls,care plan development,post-fall assessments,falls tools,fall documentation,education and training,huddles,organizational policies,rounding,reflecting substantial uptake of key BPG recommendations.Sentiment analysis demonstrated predominantly neutral or positive sentiments across implementation narratives,with variability indicating differences in implementation experience.Gaps were most evident in documentation,i.e.,post-fall follow-up actions and policy-level strategies,suggesting opportunities to strengthen implementation fidelity.Conclusions The study identified a core set of frequently implemented falls prevention strategies in LTC settings.These findings provide actionable guidance for clinical practice by emphasizing the need to standardize risk screening and reassessment processes,strengthen post-fall evaluation and follow-up,improve documentation systems to support continuity of care,and implement ongoing,competency-based education for staff.Together,these targeted strategies can support more consistent translation of evidence-based guidelines into routine practice and enhance quality-improvement efforts in falls prevention in LTC settings. 展开更多
关键词 Artificial intelligence Best practice guideline Falls Implementation science Long-term care Natural language processing Nursing
暂未订购 下载PDF
Advancing Large Language Models for Low-Resource Languages:A Systematic Review of Pretraining,Adaptation,and Ethical Challenges 认领 引用
19
作者 Ismail Hossain Mridul Banik +2 位作者 Fahmid Al Farid Jia Uddin Hezerul bin Abdul Karim 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第7期122-159,共38页
In recent years,the rapid advancement of Large Language Models(LLMs)has significantly transformed natural language processing(NLP),enabling impressive performance across a wide range of tasks.However,these development... In recent years,the rapid advancement of Large Language Models(LLMs)has significantly transformed natural language processing(NLP),enabling impressive performance across a wide range of tasks.However,these developments have largely benefited high-resource languages,leaving many low-resource and underrepresented languages at risk of further digital marginalization.Addressing this imbalance is crucial to building more inclusive and culturally sustainable AI systems,which is motivating growing research interest in adapting LLMs for linguistically diverse and resource-scarce communities.This systematic review examines recent progress(2020–2025)in the pretraining and adaptation of LLMs for Low-Resource Languages(LRLs).Analysed 812 records obtained in the large databases and using PRISMA criteria,140 core studies were identified.The innovations in data augmentation and parameter-efficient fine-tuning approaches can be outlined in this selection process.It combines major innovations on data-driven augmentation,parameter-efficient fine-tuning and morphologically rich and underrepresented language script-sensitive tokenization.The results highlight the growing effectiveness of culturally aware standards such as IrokoBench and BLEnD and show that approaches to lightweight adaptation eliminate high computational costs while maintaining language accuracy.The review focuses on the ethics in AI practice,the development of corpora through communities,and interdisciplinary research collaboration among computational linguists,social scientists,and digital humanists.The task of generating a diversified dataset,typology-conscious modelling strategies,and open-source multilingual benchmarks should be prioritized in future research as one possible solution to the existing digital language gap worldwide. 展开更多
关键词 LLMs low-resource languages(LRLs) parameter-efficient fine-tuning(PEFT) tokenization cross-lingual transfer multilingual benchmarks
暂未订购 下载PDF
A Narrative Inquiry of a University English Teacher’s Emotional Experience and Identity Construction in Mobile-Assisted Language Learning 认领 引用
20
作者 Tao Zeng Chang Xu Heng Zhang 《Chinese Journal of Applied Linguistics》 2026年第2期255-273,321,共19页
Mobile-Assisted Language Learning(MALL)has garnered substantial attention due to its demonstrated potential for significantly enhancing learner engagement and instructional effectiveness.However,current research prima... Mobile-Assisted Language Learning(MALL)has garnered substantial attention due to its demonstrated potential for significantly enhancing learner engagement and instructional effectiveness.However,current research primarily foregrounds learners’experiences,often overlooking the emotional trajectories and teachers’identity construction during its implementation.Grounded in Sociocultural Theory(SCT),this study employs a narrative approach to examine the emotional evolution and identity transformation of a university English teacher adopting MALL.Drawing on nearly four years of empirical data—including interviews,dialogues,and reflective journals—the analysis reveals that the teacher progressed through three distinct identity stages:a conservative novice,a natural user,and an enthusiastic adopter.Each stage aligned with an emotional transition,moving from anxiety to acceptance and,ultimately,to confidence.His internalization of MALL unfolded across three sequential phases:establishing connections,deepening learning,and engaging in critical reflection.This study underscores the dynamic interplay between emotion and identity and posits that effective technology integration must attend to teachers’emotional support needs.The findings may offer valuable insights for the professional development of university English teachers and for the strategic integration of educational technology. 展开更多
关键词 mobile-assisted language learning emotional experience identity construction narrative inquiry university English teacher
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