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34篇文章
< 1 2 >
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：
Enhancing Power Enterprise Inspection and Supervision: A LoRA-Based Lightweight LLM Framework Integrating Retrieval-Augmented Generation and Prompt Engineering 认领 引用
1
作者 Jianfeng Liu Yongjiao Yang +4 位作者 Kangyi Yang Changhua Hu Zijia Xu Qingguo Shi Yi Su 《Computers, Materials & Continua》 SCIE EI 2026年第8期2256-2275,共20页
Power enterprise inspection and supervision require greater intelligence,efficiency,and standardization;however,existing approaches are limited by inefficient knowledge retrieval,inaccurate issue identification,and in... Power enterprise inspection and supervision require greater intelligence,efficiency,and standardization;however,existing approaches are limited by inefficient knowledge retrieval,inaccurate issue identification,and insufficient support for standardized reporting and rectification tracking.This study proposes a lightweight,domain-adaptive large language model(LLM)framework based on Low-Rank Adaptation(LoRA),integrating Retrieval-Augmented Generation(RAG)and structured prompt engineering to enable evidence-grounded inspection tasks.The framework achieves parameter-efficient adaptation through low-rank decomposition and constructs a domain-specific multimodal knowledge base,enhancing output traceability,consistency,and task generalization.A key contribution is the introduction of a Sensitive Information Control Gate,which enforces role-based access control and automated redaction,ensuring secure and compliant generation in regulated environments while preserving traceability.Experimental results demonstrate that the proposed method achieves improved performance over the base model and demonstrates competitive effectiveness under the evaluated conditions,supported by statistical analysis(paired t-test,p<0.01,bootstrap 95%confidence intervals),while maintaining high parameter efficiency with only 0.4%–0.5%trainable parameters. 展开更多
关键词 Large language models LoRA fine-tuning retrieval-augmented generation prompt engineering inspection and supervision power enterprise governance
暂未订购 下载PDF
Chronological Passage Assembly for Retrieval-Augmented Generation in Narrative Question Answering 认领 引用
2
作者 Byeongjeong Kim Jeonghyun Park +1 位作者 Joonho Yang Hwanhee Lee 《Computers, Materials & Continua》 SCIE EI 2026年第9期2167-2187,共21页
Long-context question answering over narrative documents remains challenging because many questions require reconstructing event sequences while preserving local contextual flow under limited context budgets.Existing ... Long-context question answering over narrative documents remains challenging because many questions require reconstructing event sequences while preserving local contextual flow under limited context budgets.Existing retrieval-augmented generation(RAG)methods typically retrieve document snippets independently,which can fragment narratives and harm temporal dependencies.We propose ChronoRAG,a retrieval framework for narrative question answering that first converts sequential document chunks into concise relation descriptions and then retrieves relevant units together with their adjacent chronological context.This design preserves retrieval precision while providing the generator with coherent local narrative structure.Experiments on NarrativeQA and GutenQA show that ChronoRAG improves performance on NarrativeQA and remains competitive on GutenQA,with particularly strong gains on questions that require chronology-sensitive context.These results suggest that explicitly modeling local event order is a useful retrieval signal for narrative question answering. 展开更多
关键词 Retrieval-augmented generation narrative question answering long-context reasoning temporal reasoning knowledge graphs
暂未订购 下载PDF
Nursing Retrieval-Augmented Generation:Retrieval augmented generation for nursing question answering with large language models 认领 引用 被引量：1
3
作者 Liping Xiong Qiqiao Zeng +1 位作者 Weixiang Luo Ronghui Liu 《International Journal of Nursing Sciences》 CSCD 2025年第6期516-523,I0001,共8页
Objective:This study aimed to develop a Nursing Retrieval-Augmented Generation(NurRAG)system based on large language models(LLMs)and to evaluate its accuracy and clinical applicability in nursing question answering.Me... Objective:This study aimed to develop a Nursing Retrieval-Augmented Generation(NurRAG)system based on large language models(LLMs)and to evaluate its accuracy and clinical applicability in nursing question answering.Methods:A multidisciplinary team consisting of nursing experts,artificial intelligence researchers,and information engineers collaboratively designed the NurRAG framework following the principles of retrieval-augmented generation.The system included four functional modules:1)construction of a nursing knowledge base through document normalization,embedding,and vector indexing;2)nursing question filtering using a supervised classifier;3)semantic retrieval and re-ranking for evidence selection;and 4)evidence-conditioned language model generation to produce citation-based nursing answers.The system was securely deployed on hospital intranet servers using Docker containers.Performance evaluation was conducted with 1,000 expert-verified nursing question–answer pairs.Semantic fidelity was assessed using Recall Oriented Understudy for Gisting Evaluation–Longest Common Subsequence(ROUGE-L),and clinical correctness was measured using Accuracy.Results:The NurRAG system achieved significant improvements in both semantic fidelity and answer accuracy compared with conventional large language models.For ChatGLM2-6B,ROUGE-L increased from(30.73±1.48)%to(64.27±0.27)%,and accuracy increased from(49.08±0.92)%to(75.83±0.35)%.For LLaMA2-7B,ROUGE-L increased from(28.76±0.89)%to(60.33±0.21)%,and accuracy increased from(43.27±0.83)%to(73.29±0.33)%.All differences were statistically significant(P<0.001).A quantitative case analysis further demonstrated that NurRAG effectively reduced hallucinated outputs and generated evidence-based,guideline-concordant nursing responses.Conclusion:The NurRAG system integrates domain-specific retrieval with LLMs generation to provide accurate,reliable,and traceable evidence-based nursing answers.The findings demonstrate the system’s feasibility and potential to improve the accuracy of clinical knowledge access,support evidence-based nursing decision-making,and promote the safe application of artificial intelligence in nursing practice. 展开更多
关键词 Evidence-based nursing Large language models Nursing knowledge base Question-answering system Retrieval-augmented generation
暂未订购 下载PDF
A Dynamic Knowledge Base Updating Mechanism-Based Retrieval-Augmented Generation Framework for Intelligent Question-and-Answer Systems 认领 引用 被引量：2
4
作者 Yu Li 《Journal of Computer and Communications》 2025年第1期41-58,共18页
In the context of power generation companies, vast amounts of specialized data and expert knowledge have been accumulated. However, challenges such as data silos and fragmented knowledge hinder the effective utilizati... In the context of power generation companies, vast amounts of specialized data and expert knowledge have been accumulated. However, challenges such as data silos and fragmented knowledge hinder the effective utilization of this information. This study proposes a novel framework for intelligent Question-and-Answer (Q&A) systems based on Retrieval-Augmented Generation (RAG) to address these issues. The system efficiently acquires domain-specific knowledge by leveraging external databases, including Relational Databases (RDBs) and graph databases, without additional fine-tuning for Large Language Models (LLMs). Crucially, the framework integrates a Dynamic Knowledge Base Updating Mechanism (DKBUM) and a Weighted Context-Aware Similarity (WCAS) method to enhance retrieval accuracy and mitigate inherent limitations of LLMs, such as hallucinations and lack of specialization. Additionally, the proposed DKBUM dynamically adjusts knowledge weights within the database, ensuring that the most recent and relevant information is utilized, while WCAS refines the alignment between queries and knowledge items by enhanced context understanding. Experimental validation demonstrates that the system can generate timely, accurate, and context-sensitive responses, making it a robust solution for managing complex business logic in specialized industries. 展开更多
关键词 Retrieval-Augmented Generation Question-and-Answer Large Language Models Dynamic Knowledge Base Updating Mechanism Weighted Context-Aware Similarity
暂未订购 下载PDF
The Semantic Design Space of Retrieval-Augmented Recommender Systems:A Systematic Review of LLM-Based Approaches 认领 引用
5
作者 Minhyeok Choi Imran Ahsan +2 位作者 Hyunwook Yu Taeyoung Choe Mucheol Kim 《Computers, Materials & Continua》 SCIE EI 2026年第7期77-119,共43页
Large language models(LLMs)are increasingly integrated into recommender systems to support semantic reasoning,natural language understanding,and user-adaptive personalization.However,their reliance on static parametri... Large language models(LLMs)are increasingly integrated into recommender systems to support semantic reasoning,natural language understanding,and user-adaptive personalization.However,their reliance on static parametric knowledge and fixed representations limits robustness in dynamic environments,particularly under long-tail and cold-start conditions.Retrieval-augmented architectures have emerged to address these limitations by grounding LLMs in external,non-parametric knowledge sources.This systematic literature review synthesizes 138 peer-reviewed studies published between 2023 and 2025 in conferences and journals,focusing on retrieval-augmented and LLM-enhanced recommendation.We analyze these works through a three-dimensional framework covering:(i)domain application,(ii)semantic feature and representation design,and(iii)algorithmic strategies for retrieval and personalization.The review shows that current research is concentrated in general recommendation and information retrieval,that similarityetrieval,user-item interaction,and textual content signals dominate semantic modeling,and that LLM and BERT-style encoders form the primary representation backbones,while graph-based,multimodal,and hybrid approaches remain comparatively underexplored.Algorithmically,most systems adopt generic LLM-centric modeling with limited use of retrieval optimization,reinforcement learning,or structure-aware strategies,and only sporadic attention to explicit cold-start,hallucination,and robustness treatment.By mapping co-occurrence patterns between domains,semantic features,representation choices,and strategy families,this review identifies concrete gaps and transfer opportunities for future work on retrieval-augmented recommendation and provides a structured reference for designing more context-aware,explainable,and data-efficient LLM-based recommender systems. 展开更多
关键词 Large language models(LLMs) recommender system retrieval-augmented generation(RAG) semantic features
暂未订购 下载PDF
Retrieval-Augmented Large Language Model for AWS Cloud Threat Detection and Modelling:Cloudtrail Mitre ATT&CK Mapping 认领 引用
6
作者 Goodness Adediran Kenny Awuson-David Yussuf Ahmed 《Computers, Materials & Continua》 SCIE EI 2026年第5期2307-2331,共25页
Amazon Web Services(AWS)Cloud Trail auditing service provides detailed records of operational and security events,enabling cloud administrators to monitor user activity and manage compliance.Although signaturebased th... Amazon Web Services(AWS)Cloud Trail auditing service provides detailed records of operational and security events,enabling cloud administrators to monitor user activity and manage compliance.Although signaturebased threat detection methods have been enhanced with machine learning and Large Language Models(LLMs),these approaches remain limited in addressing emerging threats.This study evaluates a two-step Retrieval Augmented Generation(RAG)approach using Gemini 2.5 Pro to enhance threat detection accuracy and contextual relevance.The RAG system integrates external cybersecurity knowledge sources including the MITRE ATT&CK framework,AWS Threat Technique Catalogue,and threat reports to overcome limitations of static pre-trained LLMs.We constructed an evaluation dataset of 200 unique CloudTrail events(122 malicious,78 benign)using the Stratus Red Team adversary emulation framework,covering 9 MITRE ATT&CK techniques across 8 tactics.Events were sampled from 1724 total events using stratified sampling.Ground truth labels were created through systematic expert annotation with 90%inter-annotator agreement.The RAG-enabled model achieved estimated 78%accuracy,85%precision,and 79%F1-score,representing 70.5%accuracy improvement and 76.4%F1-score improvement over baseline Gemini 2.5 Pro(46%accuracy,45%F1-score).Performance are based on evaluation results on 200-event dataset.Cost-latency analysis revealed processing time of 4.1 s and cost of$0.00376 per event,comparable to commercial SIEM solutions while providing superior MITRE ATT&CK attribution.The findings demonstrate that RAG substantially enhances context-aware threat detection,providing actionable insights for cloud security operations. 展开更多
关键词 Retrieval-augmented generation Amazon web services LLM cloud service provider threat detection threat modelling MITRE ATT&CK RAG-enabled model RAG-enabled LLM system
暂未订购 下载PDF
From Documents to Decisions:Enterprise-Grade LLM Systems for Zero-Hallucination,Attributed Generation,and Regulatory Alignment 认领 引用
7
作者 Yenjou Wang Chihtan Cheng Jia-Wei Chang 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第5期270-324,共55页
As large language models(LLMs)become increasingly integrated into enterprise decision-making processes,structural pressures such as version drift,cross-source evidence integration,and regulatory accountability have sh... As large language models(LLMs)become increasingly integrated into enterprise decision-making processes,structural pressures such as version drift,cross-source evidence integration,and regulatory accountability have shifted the primary challenge from isolated generative performance to system-level consistency,traceability,and governability.This paper systematically reviews key technological developments relevant to enterprise requirements,including document perception,retrieval-augmented generation(RAG),hybrid RAG-KG architectures,fine-grained attribution evaluation,and multi-agent coordination.The analysis demonstrates that the main obstacle to enterprise LLM adoption is not model capability,but rather the structural gap between fragmented technical modules and the need for high-reliability decision-making.In response,a risk-controlled data flywheel architecture is proposed that integrates perception,reasoning,verification,and governance layers.By converting reasoning outputs into observable risk signals and feeding them back into retrieval and structural components,this architecture establishes a continuous improvement loop.This approach provides a systematic deployment blueprint for enterprise-grade LLM systems,emphasizing traceability,accountability,and sustainable optimization in high-risk and long-term operational contexts. 展开更多
关键词 Large language models(LLMs) retrieval-augmented generation(RAG) knowledge graph(KG) optical character recognition(OCR) enterprise AI systems risk-controlled architecture governance and compliance attribution and faithfulness multi-agent systems data flywheel
暂未订购 下载PDF
Improving Clinical Support through Retrieval-Augmented Generation Powered Virtual Health Assistants 认领 引用
8
作者 Biju Baburajan Anandavally 《Journal of Computer and Communications》 2024年第11期86-94,共9页
This article examines the implementation of a virtual health assistant powered by Retrieval-Augmented Generation (RAG) and GPT-4, aimed at enhancing clinical support through personalized, real-time interactions with p... This article examines the implementation of a virtual health assistant powered by Retrieval-Augmented Generation (RAG) and GPT-4, aimed at enhancing clinical support through personalized, real-time interactions with patients. The system is hypothesized to improve healthcare accessibility, operational efficiency, and patient outcomes by automating routine tasks and delivering accurate health information. The assistant leverages natural language processing and real-time data retrieval models to respond to patient inquiries, schedule appointments, provide medication reminders, assist with symptom triage, and answer insurance-related questions. By integrating RAG-based virtual care, the system reduces the burden on healthcare specialists and helps mitigate healthcare disparities, particularly in rural areas where traditional care is limited. Although the initial scope of testing did not validate all potential benefits, the results demonstrated high patient satisfaction and strong response accuracy, both critical for systems of this nature. These findings underscore the transformative potential of AI-driven virtual health assistants in enhancing patient engagement, streamlining operational workflows, and improving healthcare accessibility, ultimately contributing to better outcomes and more cost-effective care delivery. 展开更多
关键词 Retrieval-Augmented Generation (RAG) GPT-4 Healthcare Assistants Artificial Intelligence
暂未订购 下载PDF
Bailicai:A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications 认领 引用
9
作者 Long Cui Yongbin Liu +4 位作者 Chunping Ouyang Ying Yu Jiangtao Zhang Yaping Wan Fei Yang 《Big Data Mining and Analytics》 EI CSCD 2026年第2期376-392,共17页
Large language models(LLMs)excel in various natural language processing tasks and are increasingly applied in specialized fields like medicine.However,their deployment in the medical domain is challenged by limited do... Large language models(LLMs)excel in various natural language processing tasks and are increasingly applied in specialized fields like medicine.However,their deployment in the medical domain is challenged by limited domain-specific data and the tendency to generate inaccurate information,known as“hallucinations.”While domainspecific fine-tuning has improved open-source LLMs,they still underperform compared to proprietary models like ChatGPT and PaLM.To address this gap,retrieval-augmented generation(RAG)techniques have been explored to enhance LLMs by integrating external knowledge bases.Nevertheless,the success of RAG depends on the quality of retrieved documents,and its application within the medical field remains in the early stages.In this paper,we introduce the“Bailicai”framework as an exploratory approach to integrating RAG with LLMs in the medical field.The framework employs fine-tuning to improve the RAG process,where“falsely relevant”and“completely irrelevant”interference documents are intentionally included in the training data.This enables Bailicai to develop the ability to assess the quality of retrieved documents and selectively incorporate them.The framework is organized into four modules:(1)medical knowledge injection,(2)self-knowledge boundary identification,(3)directed acyclic graph task decomposition,and(4)retrieval-augmented generation.Through the synergy of these modules,Bailicai achieves superior performance on multiple medical benchmarks,outperforming existing large models in the medical domain,RAG-based methods,and proprietary models such as GPT-3.5.Furthermore,Bailicai effectively mitigates the hallucination problem common in LLMs applied to medical tasks and enhances the robustness of RAG when dealing with irrelevant or misleading documents,enabling more accurate information retrieval and integration. 展开更多
关键词 large language models(LLMs) retrieval-augmented generation(RAG) domain-specific language models
基于智能体的水利科技报告形式审查系统构建研究 认领 引用
10
作者 周逸凡 段浩 +3 位作者 王建华 赵红莉 刘诗达 谈幸燕 《水利学报》 EI CSCD 北大核心 2026年第7期1106-1116,共11页
报告审查作为项目质量控制的核心环节,传统人工审查方法存在一定的效率挑战和标准执行不一致等问题,现有通用审查系统难以适应水利科技报告结构复杂、审查任务多维与领域知识依赖的多重挑战。为此,本研究提出基于智能体的水利科技报告... 报告审查作为项目质量控制的核心环节,传统人工审查方法存在一定的效率挑战和标准执行不一致等问题,现有通用审查系统难以适应水利科技报告结构复杂、审查任务多维与领域知识依赖的多重挑战。为此,本研究提出基于智能体的水利科技报告形式审查系统架构。通过智能体驱动的动态任务规划与协同审查机制,实现对复杂报告结构的自适应解析与多任务编排;形成了基于LoRA微调和检索增强生成技术的水利领域知识增强机制,构建了包含27005条水利专业术语的术语知识库和计算关系库,形成10358个样本的指令微调数据集,提升了系统在专业术语、计算逻辑及合同一致性等任务上的审查能力。以人工审查结果为基准,智能体系统对八类审查任务的F1均值在80%以上。实验结果表明:该系统实现了水利科技报告形式审查的全流程智能化处理,显著提升效率的同时保障了审查准确率。本研究构建的智能审查系统为水利项目文档质量管理提供了标准化工具支撑,为专业领域文本智能化审查提供了可参考的技术路径。 展开更多
关键词 智能体 报告智能审查 大语言模型 Retrieval-Augmented Generation(RAG) LoRA微调
暂未订购 下载PDF
Semantic Feedback-Based RAG for Radiology Report Generation 认领 引用
11
作者 Xing Jia Yun Xiong +3 位作者 Songwen Pei Yumeng Zhang Cairong Yan Zhijun Fang 《Big Data Mining and Analytics》 EI CSCD 2026年第2期393-406,共14页
Radiology report generation aims to produce textual reports automatically based on input images,a critical process that aids in accurate diagnoses and lightens the workload of radiologists.Following recent advances in... Radiology report generation aims to produce textual reports automatically based on input images,a critical process that aids in accurate diagnoses and lightens the workload of radiologists.Following recent advances in Large Language Models(LLMs),several Retrieval-Augmented Generation(RAG)based report generation models have been proposed.Despite the continuously improved performance,these report generation models often suffer from two main limitations,i.e.,interference of irrelevant information,and lack of alignment between the input image and the resulting generated report.In this study,we propose the Semantic feedback based RAG Radiology report generation model,namely RAGSemRad.RAGSemRad comprises two key components:the fine-grained semantic retrieval module and the semantic assessment module.The fine-grained semantic retrieval module is designed to retrieve adequate and relevant prompt information,while ignoring irrelevant interference.This is achieved by clustering the data at the semantic level and leveraging the domain knowledge within a large pre-trained visual-language model,thus alleviating the issues of hallucination and databias.Further,the semantic assessment module enhances the performance of the upper bound by enhancing the alignment between the input image and the resulting generated report,utilizing supervision signals derived from paired image-label data.Experimental evaluations are conducted on two benchmarks,IU X-Ray and MIMIC-CXR,to assess the performance of RAGSemRad.The results demonstrate RAGSemRad exhibits competitive performance compared to the state-of-the-art methods,showcasing its potential to advance automatic radiology report generation. 展开更多
关键词 radiology report generation Retrieval-Augmented Generation(RAG) semantic assessment
Retrieval-Edited Generation:Mitigating Prototype Mismatches for Context-Aware Machine Translation Enhancement 认领 引用
12
作者 Ting Wang Zhiqiang Yu +1 位作者 Shihu Liu Zuo Jiang 《Data Intelligence》 EI CSCD 2026年第2期428-452,共25页
Prototype-based methods have demonstrated effectiveness in enhancing neural machine translation by leveraging similar examples for guidance.However,retrieved prototypes often suffer from semantic deviations compared t... Prototype-based methods have demonstrated effectiveness in enhancing neural machine translation by leveraging similar examples for guidance.However,retrieved prototypes often suffer from semantic deviations compared to the true translation targets.To address this issue,this paper proposes a unified Retrieval-Edited Generation(REG)framework that enhances translation quality by editing retrieved prototypes to better align with the source sentence,and this framework is applicable to both supervised neural models and Large Language Models(LLMs).Specifically,REG first retrieves the most similar target language sentence from a local corpus as a prototype based on the given source language sentence,and edits it to reduce semantic deviation.Then,the edited prototype is used to guide translation generation in supervised setting or LLM-based setting.For supervised settings,the edited prototype and source sentence are jointly processed via a dual-encoder architecture,enabling richer contextual understanding.For LLMs settings,the edited prototype is injected into the prompt following a Retrieval-Augmented Generation(RAG)paradigm,effectively guiding output generation.Experiments on multiple translation benchmarks demonstrate that the REG model can effectively enhance prototype quality while reducing noise,outperforming strong baseline models and validating the efficacy and versatility of prototype editing in modern translation workflows. 展开更多
关键词 Neural machine translation Prototype Retrieval-augmented generation Editing Denoising
From Static to Streaming:A Systematic Review and Event-Sourced Framework for GraphRAG in AIOps 认领 引用
13
作者 Ferenc Erdös Vijayakumar Varadarajan +1 位作者 Viorel-Costin Banta Stephen Afrifa 《Computers, Materials & Continua》 SCIE EI 2026年第9期98-126,共29页
Standard retrieval-augmented generation(RAG)can perform poorly in AI for IT Operations(AIOps)settings because it is topology-blind.Basic RAG retrieves isolated,flat text snippets without enforcing structural or causal... Standard retrieval-augmented generation(RAG)can perform poorly in AI for IT Operations(AIOps)settings because it is topology-blind.Basic RAG retrieves isolated,flat text snippets without enforcing structural or causal constraints,causing large language models to generate explanations that contradict the running system’s actual dependency structure.To address this gap,we conducted a systematic review following PRISMA 2020,searching Scopus,IEEE Xplore,Web of Science,and Google Scholar(last searched 31 January 2026).We included empirical or systems-oriented studies applying graph-based retrieval to ground a generative model in an IT,cloud,or softwareoperations setting,and excluded generic RAG without an operational context and graph-only methods without a generative component.Of 139 unique records,31 met the criteria.Because reported metrics,tasks,and hardware were too heterogeneous for pooled effect estimates,we performed a descriptive quantitative synthesis of reporting frequencies for five outcome variables(localization accuracy,text/classification scores,MTTR,retrieval/inference latency,and graph construction cost),with values harmonized to common units.The synthesis reveals that hybridfusion approaches have become the dominant retrieval strategy,outpacing standalone traversal in adoption for Root Cause Analysis(RCA)tasks by fusing semantic vector search with strict structural constraints.However,our evaluation matrix exposes a critical production barrier:in 73%of Service Dependency Graph(SDG)-centric studies,topology drift or streaming-update handling is not explicitly described,with many pipelines evaluated on static or periodically refreshed snapshots.We outline Event-Sourced Streaming GraphRAG(ES-GraphRAG)as a reference architecture that frames concrete design requirements for latency and drift constraints based on an event-sourced,streaming construction pattern for snapshot-consistent retrieval.The framework also incorporates strict retrievaltime governance and budget-aware traversal to help keep LLM grounding topologically accurate and compliant with incident-response Service Level Objectives(SLOs). 展开更多
关键词 Knowledge graphs retrieval-augmented generation(RAG) GraphRAG AIOps IT operations root cause analysis
暂未订购 下载PDF
Intra-Video Temporal-Aware RAG: A Self-Contained Framework for Video-Based Question Answering 认领 引用
14
作者 Sumaira Shafiq Naveed Ejaz +3 位作者 Munam Ali Shah Rashid Kamal Adnan Sohail Sheraz Aslam 《Computers, Materials & Continua》 SCIE EI 2026年第8期2276-2301,共26页
Lecture videos are widely used in modern education,yet answering questions from them remains challenging.Relevant information is often distributed across time and expressed through multiple modalities,including speech... Lecture videos are widely used in modern education,yet answering questions from them remains challenging.Relevant information is often distributed across time and expressed through multiple modalities,including speech,slides,and visual content.Existing VideoQA approaches,including recent retrieval-augmented generation(RAG)methods,typically rely on static text representations or global video features.Consequently,they may retrieve evidence that is semantically relevant but temporally misaligned,leading to inaccurate or weakly grounded responses.In addition,dependence on external knowledge sources can introduce hallucinations and reduce reliability in educational settings.To address these limitations,we propose a temporally aware,intra-video RAG framework tailored for lecture videos.The approach aligns automatic speech transcripts and visual captions into timestamped segments and performs retrieval constrained by temporal boundaries.Retrieved segments are further refined using a cross-encoder before answer generation,ensuring that responses are grounded in the correct portions of the video.We evaluate the proposed method on the LectQA-Vid dataset,consisting of 100 lecture videos and 3000 temporally annotated questions.Experimental results demonstrate improved factual alignment and robustness over non-temporal baselines,highlighting the importance of temporal grounding in lecture VideoQA. 展开更多
关键词 Video question answering retrieval-augmented generation temporal grounding multimodal retrieval educational videos whisper ASR visual captioning large language models explainable AI timestamped evidence
暂未订购 下载PDF
Evaluating Ontology-Based Function Definitions for MCP Invocation Accuracy in LLM Agent-Based HPC Systems 认领 引用
15
作者 Yejin Kwon Jeongcheol Lee Youngbom Park 《Computers, Materials & Continua》 SCIE EI 2026年第8期1136-1163,共28页
The web-based High-Performance Computing(HPC)platform provides a simulation environment that enables users to perform computational science and engineering tasks through web services,thereby eliminating the need for c... The web-based High-Performance Computing(HPC)platform provides a simulation environment that enables users to perform computational science and engineering tasks through web services,thereby eliminating the need for complex terminal-based environments.Notwithstanding the aforementioned advantages,extant platforms frequently necessitate a considerable degree of user expertise,whilst the intricacy of simulation configuration and execution engenders limitations in terms of accessibility and usability.Furthermore,while Retrieval-Augmented Generation(RAG)-based systems are effective for information retrieval,they are insufficient for accurately constructing and invoking executable service tools.In order to address these limitations,this study proposes a user agent system integrated within a web-based HPC simulation environment,said system being based on an LLM.The proposed system enhances user understanding of available applications and execution workflows,and supports precise configuration and execution of simulations.In order to facilitate practical service tool invocation,the system integrates Model Context Protocol(MCP)-based service tools and introduces an ontology-driven approach for object normalization and relational definition.The system leverages the structured relationships among service tools,transforming LLM outputs into actionable and accurate inputs for service execution.The experimental results demonstrate that the proposed approach significantly improves the accuracy of MCP-based service tool invocation and the appropriateness of responses when compared to conventional RAG-based methods.The proposed system enhances the accessibility and usability of HPC platforms and provides a practical framework for LLM-driven service automation. 展开更多
关键词 HPC platform ontology RAG(retrieval-augmented generation) LLM(large language model) model context protocol(MCP)
暂未订购 下载PDF
基于可信度感知的多策略图RAG问答研究 认领 引用
16
作者 罗一雄 滕尚志 +1 位作者 吕学强 游新冬 《北京信息科技大学学报（自然科学版）》 2026年第2期45-56,共12页
针对通用大语言模型在军事、医疗、金融等专业问答场景中幻觉严重、专业性不足的问题,以及检索增强生成(retrieval-augmented generation,RAG)技术缓解模型幻觉过程中易受检索文档虚假信息误导的新问题,提出一种可信度感知多策略图RAG(c... 针对通用大语言模型在军事、医疗、金融等专业问答场景中幻觉严重、专业性不足的问题,以及检索增强生成(retrieval-augmented generation,RAG)技术缓解模型幻觉过程中易受检索文档虚假信息误导的新问题,提出一种可信度感知多策略图RAG(credibility-aware multistrategy graph RAG,CAMG-RAG)框架,构建“可信知识生成—高可信信息检索—注意力权重优化”三级协同架构。首先,通过改进的知识图谱链接器生成含实体、关系、三元组及可信度评分的图构件;其次,基于可信度评估机制,实现多策略图检索;最后,定位大模型中对知识图谱元素敏感的“有影响力注意力头”,依据可信度评分修正其注意力权重,引导模型优先聚焦高价值知识。实验结果表明,在军事领域QAonMilitaryKG数据集上,CAMG-RAG能够显著提高大模型对抗幻觉的能力,基于Qwen3-4B模型,其忠实度、答案正确性分别达到0.746、0.863,比微调大模型提高14.6%、5.9%。 展开更多
关键词 大语言模型 检索增强生成(retrieval-augmented generation,RAG) 问答系统 知识图谱
暂未订购 下载PDF
Transforming Healthcare with State-of-the-Art Medical-LLMs:A Comprehensive Evaluation of Current Advances Using Benchmarking Framework 认领 引用
17
作者 Himadri Nath Saha Dipanwita Chakraborty Bhattacharya +5 位作者 Sancharita Dutta Arnab Bera Srutorshi Basuray Satyasaran Changdar Saptarshi Banerjee Jon Turdiev 《Computers, Materials & Continua》 SCIE EI 2026年第2期234-289,共56页
The emergence of Medical Large Language Models has significantly transformed healthcare.Medical Large Language Models(Med-LLMs)serve as transformative tools that enhance clinical practice through applications in decis... The emergence of Medical Large Language Models has significantly transformed healthcare.Medical Large Language Models(Med-LLMs)serve as transformative tools that enhance clinical practice through applications in decision support,documentation,and diagnostics.This evaluation examines the performance of leading Med-LLMs,including GPT-4Med,Med-PaLM,MEDITRON,PubMedGPT,and MedAlpaca,across diverse medical datasets.It provides graphical comparisons of their effectiveness in distinct healthcare domains.The study introduces a domain-specific categorization system that aligns these models with optimal applications in clinical decision-making,documentation,drug discovery,research,patient interaction,and public health.The paper addresses deployment challenges of Medical-LLMs,emphasizing trustworthiness and explainability as essential requirements for healthcare AI.It presents current evaluation techniques that improve model transparency in high-stakes medical contexts and analyzes regulatory frameworks using benchmarking datasets such asMedQA,MedMCQA,PubMedQA,and MIMIC.By identifying ongoing challenges in biasmitigation,reliability,and ethical compliance,thiswork serves as a resource for selecting appropriate Med-LLMs and outlines future directions in the field.This analysis offers a roadmap for developing Med-LLMs that balance technological innovation with the trust and transparency required for clinical integration,a perspective often overlooked in existing literature. 展开更多
关键词 Medical large language models(Med-LLM) AI in healthcare natural language processing(NLP)in medicine fine-tuning medical LLMs retrieval-augmented generation(RAG)in medicine multi-modal learning in healthcare explainability and transparency in medical AI FDA regulations for AI in medicine evaluation and benchmarking of medical large language models
暂未订购 下载PDF
Research on Agricultural Machinery Fault Nested Entity Extraction for Low-Resource and High-Noise Scenes 认领 引用
18
作者 Huaixuan Yan Yan Gong 《Computers, Materials & Continua》 SCIE EI 2026年第8期1769-1793,共25页
To correctly diagnose faults in farm machinery,we need to know a lot about the field and have experience with maintenance.However,most of this important information is stored in old,unstructured documents like technic... To correctly diagnose faults in farm machinery,we need to know a lot about the field and have experience with maintenance.However,most of this important information is stored in old,unstructured documents like technical manuals and expert logs.These documents don’t have a standard way to be represented digitally,which makes it very hard to build automated diagnosis systems.There are three main technical problems with getting structured knowledge out of this kind of text:noise from optical character recognition(OCR)during digitization,the extreme lack of labeled samples in specialized fields(low-resource constraints),and the complex nested structures that are common in descriptions of mechanical components.To fill this gap in research,this paper suggests a semantic-enhanced nested entity extraction framework that is made for situations with few resources and a lot of noise.To fill this gap in research,this paper suggests a semantic-enhanced nested entity extraction framework engineered specifically for low-resource and high-noise constraints.First,to mitigate the severe visual noise inherent in digitized legacy documents,we introduce a Targeted Noise-Injection Denoising Paradigm.This module utilizes whole-word masking to simulate and correct OCR character confusion prior to feature extraction.Second,to overcome extreme data sparsity,we propose a Dynamic Domain-Constrained Augmentation Algorithm.Governed by a TF-IDF-weighted substitution formula,this algorithm mathematically isolates and preserves high-information domain entities while expanding the syntactic feature space.Finally,we architect a Hierarchical Span-Decoding Network.By integrating contextual word embeddings with bidirectional temporal gating and a global pointer matrix,this network transcends the“flat”assumptions of traditional sequence labeling to accurately identify multi-level nested entities,such as parts-assembly relationships.Experimental results demonstrate that the proposed framework achieves an F1-score of 95.87%with minimal seed data.Ablation studies also show that the data augmentation strategy leads to big performance gains.Moreover,by employing this method,we create a fault knowledge graph comprising 19,710 entities and validate the efficacy of converting unstructured text into computable fault knowledge via a Retrieval-Augmented Generation(RAG)system. 展开更多
关键词 Agricultural machinery knowledge graph fault diagnosis named entity recognition data augmentation nested entity extraction retrieval-augmented generation
暂未订购 下载PDF
Research on Chinese text correction methods based on retrieval-augmented candidate re-ranking 认领 引用
19
作者 Tong Zhang 《Advances in Engineering Innovation》 2026年第6期150-162,共13页
As one of the fundamental tasks in natural language processing,Chinese spelling correction aims to automatically detect and correct typos and non-standard expressions in texts.In recent years,Large Language Models(LLM... As one of the fundamental tasks in natural language processing,Chinese spelling correction aims to automatically detect and correct typos and non-standard expressions in texts.In recent years,Large Language Models(LLMs)have opened up a new avenue for text correction by virtue of their vast knowledge networks and superior reasoning capabilities.However,when directly used as end-to-end generators,they are highly prone to over-correction and semantic drift,undermining the objective fidelity of the original text.To address these issues,this paper proposes a Chinese Spelling Correction(CSC)method based on Retrieval-augmented Candidate Re-ranking(R2-CSC).This method first adopts dual heterogeneous small models for front-end scanning to locate error positions.After replacing each error position with a mask token,retrieval is performed in a vector database.Subsequently,the system concatenates the retrieval results with the original sentence into a structured prompt,driving the large language model to generate high-quality correction candidates under the iterative control of a discriminator and construct a multi-source heterogeneous candidate set.In the decision-making stage,a joint scoring re-ranking mechanism is employed to comprehensively calculate the perplexity,semantic similarity and correct character retention rate of candidate sentences,and select the optimal solution under multi-dimensional feature weighting.In addition,the framework incorporates a commonsense error diagnosis module to conduct fact-checking on the final result via non-intrusive prompts.Experiments are conducted on the benchmark datasets SIGHAN13,SIGHAN14 and SIGHAN15.The results show that the sentence-level correction F1-scores of R2-CSC reach 85.2%,70.2%and 81.5%respectively,which is an improvement of more than 21 percentage points over the baseline of direct generation by large models,and outperforms traditional baseline models such as MDCSpell and REALISE.Ablation experiments further verify the contributions of the retrieval augmentation,joint re-ranking and multi-source candidate modules to the overall performance. 展开更多
关键词 Chinese spelling correction retrieval-augmented generation candidate re-ranking large language models
Overview of the Integration of Large Language Models,Knowledge Graphs,and GraphRAG,along with Research on Their Industrial Applications 认领 引用
20
作者 Xian Ye 《Journal of Electronic Research and Application》 2026年第1期36-42,共7页
In recent years,Large Language Models(LLMs)have rapidly advanced in language understanding,reasoning,and generation,and are increasingly adopted as the“brain”of industrial intelligent systems.Nevertheless,in high-ri... In recent years,Large Language Models(LLMs)have rapidly advanced in language understanding,reasoning,and generation,and are increasingly adopted as the“brain”of industrial intelligent systems.Nevertheless,in high-risk and strongly regulated domains they still exhibit hallucination,weak domain grounding,limited interpretability,and privacy as well as security constraints.Knowledge graphs(KGs)encode domain entities,relations,rules,and events explicitly,providing controllable semantics and an explainable reasoning substrate.Retrieval-augmented generation(RAG)injects external evidence into LLM prompting,while GraphRAG further introduces graph indexing and community-level retrieval to preserve global structure and support multi-hop reasoning.This review summarizes the evolution of LLMs,KG modeling and extraction,GraphRAG mechanisms,and a general fusion framework.Typical industrial applications are surveyed,and a coal mine flood emergency plan generation and evaluation approach is discussed to illustrate the practical value of graph-grounded large models.KG-enhanced retrieval also supports provenance tracking,allowing industrial users to audit the evidence behind model outputs. 展开更多
关键词 Large language model Knowledge graph GraphRAG Retrieval-augmented generation Coal mine flood Emergency management
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 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈