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
Under the paradigm of Industry 5.0,intelligent manufacturing transcends mere efficiency enhancement by emphasizing human-machine collaboration,where human expertise plays a central role in assembly processes.Despite a...Under the paradigm of Industry 5.0,intelligent manufacturing transcends mere efficiency enhancement by emphasizing human-machine collaboration,where human expertise plays a central role in assembly processes.Despite advancements in intelligent and digital technologies,assembly process design still heavily relies on manual knowledge reuse,and inefficiencies and inconsistent quality in process documentation are caused.To address the aforementioned issues,this paper proposes a knowledge push method of complex product assembly process design based on distillation model-based dynamically enhanced graph and Bayesian network.First,an initial knowledge graph is constructed using a BERT-BiLSTM-CRF model trained with integrated human expertise and a fine-tuned large language model.Then,a confidence-based dynamic weighted fusion strategy is employed to achieve dynamic incremental construction of the knowledge graph with low resource consumption.Subsequently,a Bayesian network model is constructed based on the relationships between assembly components,assembly features,and operations.Bayesian network reasoning is used to push assembly process knowledge under different design requirements.Finally,the feasibility of the Bayesian network construction method and the effectiveness of Bayesian network reasoning are verified through a specific example,significantly improving the utilization of assembly process knowledge and the efficiency of assembly process design.展开更多
Water scarcity poses a significant challenge globally,with South Africa exemplifying the severe socio-economic and environmental impacts of limited water access.Despite advances in modern water management systems,the ...Water scarcity poses a significant challenge globally,with South Africa exemplifying the severe socio-economic and environmental impacts of limited water access.Despite advances in modern water management systems,the integration of indigenous knowledge(IK)into formal frameworks remains underutilized.This study systematically reviews the role of indigenous water conservation practices in South Africa,analyzing over 50 high-quality sources using the PRISMA methodology.The findings highlight the effectiveness of IK in addressing water scarcity through techniques such as rainwater harvesting,terracing,and wetland management,which are low-cost,environmentally sustainable,and deeply rooted in cultural practices.Indigenous methods also enhance climate resilience by enabling communities to adapt to droughts and floods through practices such as weather prediction and adaptive farming techniques.Furthermore,these practices foster social inclusivity and community empowerment,ensuring equitable water access and intergenerational knowledge transfer.The study underscores the potential of integrating IK with modern water technologies to create holistic solutions that are scalable,sustainable,and aligned with South Africa’s goal of achieving water security by 2030.Policy recommendations emphasize the need for institutional support,data collection,and financial incentives to sustain and mainstream indigenous approaches.By bridging the gap between traditional and contemporary systems,this research provides a roadmap for leveraging diverse knowledge systems to address water scarcity and build resilient communities.展开更多
Xi Jinping,general secretary of the Communist Party of China(CPC)Central Committee,stressed that we should adhere to the“two integrations”(namely,integrating the basic tenets of Marxism with China’s specific realit...Xi Jinping,general secretary of the Communist Party of China(CPC)Central Committee,stressed that we should adhere to the“two integrations”(namely,integrating the basic tenets of Marxism with China’s specific realities and fine traditional culture),root ourselves in Chinese soil,carry forward the Chinese cultural heritage,and strengthen the academic foundation.We should accelerate the building of an independent knowledge system for Chinese philosophy and social sciences,and formulate original concepts and develop systems of academic discipline,research and discourse,drawing on China’s rich experience of advancing human rights.In the face of changes of a magnitude not seen in a century,in the historic process of advancing the great rejuvenation of the Chinese nation on all fronts through Chinese modernization,we should and must strengthen our theoretical self-consciousness and confidence in the path of Chinese modernization.We need to enhance human rights research,develop the human rights theoretical system and paradigm that are based on Chinese realities and express Chinese voice,and an independent Chinese knowledge system for human rights.展开更多
Recent advancements in large language models(LLMs)have driven remarkable progress in text process-ing,opening new avenues for medical knowledge discovery.In this study,we present ERQA,a mEdical knowledge Retrieval and...Recent advancements in large language models(LLMs)have driven remarkable progress in text process-ing,opening new avenues for medical knowledge discovery.In this study,we present ERQA,a mEdical knowledge Retrieval and Question-Answering framework powered by an enhanced LLM that integrates a semantic vector database and a curated literature repository.The ERQA framework leverages domain-specific incremental pretraining and conducts supervised fine-tuning on medical literature,enabling retrieval and question-answering(QA)tasks to be completed with high precision.Performance evaluations implemented on the coronavirus disease 2019(COVID-19)and TripClick data-sets demonstrate the robust capabilities of ERQA across multiple tasks.On the COVID-19 dataset,ERQA-13B achieves state-of-the-art retrieval metrics,with normalized discounted cumulative gain at top 10(NDCG@10)0.297,recall values at top 10(Recall@10)0.347,and mean reciprocal rank(MRR)=0.370;it also attains strong abstract summarization performance,with a recall-oriented understudy for gisting evaluation(ROUGE)-1 score of 0.434,and QA performance,with a bilingual evaluation understudy(BLEU)-1 score of 7.851.The comparable performance achieved on the TripClick dataset further under-scores the adaptability of ERQA across diverse medical topics.These findings suggest that ERQA repre-sents a significant step toward efficient biomedical knowledge retrieval and QA.展开更多
The global rise in animal protein consumption has significantly amplified the demand for fodder.A comprehensive understanding of the diversity and characteristics of existing fodder resources is essential for balanced...The global rise in animal protein consumption has significantly amplified the demand for fodder.A comprehensive understanding of the diversity and characteristics of existing fodder resources is essential for balanced nutritional fodder production.This study investigates the diversity and composition of fodder plants and identifies key species for cattle in Zhaotong City,Yunnan,China,while documenting indigenous knowledge on their usage and selection criteria.Ethnobotanical surveys were conducted in 19 villages across seven townships with 140 informants.Data were collected through semi-structured interviews,free listing,and participatory observation,and analyzed using Relative Frequency Citation.A total of 125 taxa(including 106 wild and 19 cultivated)were reported.The most cited family is Poaceae(27 taxa,21.43%),followed by Asteraceae(17 taxa,13.49%),Fabaceae(14 taxa,11.11%),Polygonaceae(9 taxa,7.14%)and Lamiaceae(4 taxa,3.17%).The whole plant(66.04%)and herbaceous plants(84.80%)were the most used parts and life forms.The most cited species were Zea mays,Brassica rapa,Solanum tuberosum,Eragrostis nigra,and Artemisia dubia.Usage of diverse fodder resources reflects local wisdom in managing resource availability and achieving balanced nutrition while coping with environmental and climatic risks.Preferences for certain taxonomic groups are due to their quality as premier fodder resources.To promote integrated crop-livestock farming,we suggest further research into highly preferred fodder species,focusing on nutritional assessment,digestibility,meat quality impacts,and potential as antibiotic alternatives.Establishing germplasm and gene banks for fodder resources is also recommended.展开更多
Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representati...Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representation,modeling,fusion,computation,and storage.Within this framework,knowledge extraction,as the core component,directly determines KG quality.In military domains,traditional manual curation models face efficiency constraints due to data fragmentation,complex knowledge architectures,and confidentiality protocols.Meanwhile,crowdsourced ontology construction approaches from general domains prove non-transferable,while human-crafted ontologies struggle with generalization deficiencies.To address these challenges,this study proposes an OntologyAware LLM Methodology for Military Domain Knowledge Extraction(LLM-KE).This approach leverages the deep semantic comprehension capabilities of Large Language Models(LLMs)to simulate human experts’cognitive processes in crowdsourced ontology construction,enabling automated extraction of military textual knowledge.It concurrently enhances knowledge processing efficiency and improves KG completeness.Empirical analysis demonstrates that this method effectively resolves scalability and dynamic adaptation challenges in military KG construction,establishing a novel technological pathway for advancing military intelligence development.展开更多
The rapid development of information technology and accelerated digitalization have led to an explosive growth of data across various fields.As a key technology for knowledge representation and sharing,knowledge graph...The rapid development of information technology and accelerated digitalization have led to an explosive growth of data across various fields.As a key technology for knowledge representation and sharing,knowledge graphs play a crucial role by constructing structured networks of relationships among entities.However,data sparsity and numerous unexplored implicit relations result in the widespread incompleteness of knowledge graphs.In static knowledge graph completion,most existing methods rely on linear operations or simple interaction mechanisms for triple encoding,making it difficult to fully capture the deep semantic associations between entities and relations.Moreover,many methods focus only on the local information of individual triples,ignoring the rich semantic dependencies embedded in the neighboring nodes of entities within the graph structure,which leads to incomplete embedding representations.To address these challenges,we propose Two-Stage Mixer Embedding(TSMixerE),a static knowledge graph completion method based on entity context.In the unit semantic extraction stage,TSMixerE leveragesmulti-scale circular convolution to capture local features atmultiple granularities,enhancing the flexibility and robustness of feature interactions.A channel attention mechanism amplifies key channel responses to suppress noise and irrelevant information,thereby improving the discriminative power and semantic depth of feature representations.For contextual information fusion,a multi-layer self-attentionmechanism enables deep interactions among contextual cues,effectively integrating local details with global context.Simultaneously,type embeddings clarify the semantic identities and roles of each component,enhancing the model’s sensitivity and fusion capabilities for diverse information sources.Furthermore,TSMixerE constructs contextual unit sequences for entities,fully exploring neighborhood information within the graph structure to model complex semantic dependencies,thus improving the completeness and generalization of embedding representations.展开更多
This paper delves into effective pathways for transforming course ecosystems from resource provision to knowledge service and competency development through university-enterprise collaboration in co-building knowledge...This paper delves into effective pathways for transforming course ecosystems from resource provision to knowledge service and competency development through university-enterprise collaboration in co-building knowledge graphs and intelligent shared courses.This approach enables personalized,learning-driven teaching.Based on knowledge graphs and integrated teacher-machine-student smart teaching scenarios,it not only innovates autonomous learning environments and human-computer interaction models while optimizing teaching experiences for both instructors and students,but also effectively addresses the issues of students’“scattered,superficial,and fragmented learning”.This establishes the foundation for personalized teaching tailored to individual aptitudes.展开更多
This paper proposes a deep learning-based 3D LiDAR perception framework designed for applications such as autonomous robots and vehicles.To address the high dependency on large-scale annotated data—an inherent limita...This paper proposes a deep learning-based 3D LiDAR perception framework designed for applications such as autonomous robots and vehicles.To address the high dependency on large-scale annotated data—an inherent limitation of deep learning models—this study introduces a hybrid perception architecture that incorporates expertdriven LiDAR processing techniques into the deep neural network.Traditional 3DLiDAR processingmethods typically remove ground planes and apply distance-or density-based clustering for object detection.In this work,such expert knowledge is encoded as feature-level inputs and fused with the deep network,therebymitigating the data dependency issue of conventional learning-based approaches.Specifically,the proposedmethod combines two expert algorithms—Patchwork++for ground segmentation and DBSCAN for clustering—with a PointPillars-based LiDAR detection network.We design four hybrid versions of the network depending on the stage and method of integrating expert features into the feature map of the deep model.Among these,Version 4 incorporates a modified neck structure in PointPillars and introduces a new Cluster 2D Pseudo-Map Branch that utilizes cluster-level pseudo-images generated from Patchwork++and DBSCAN.This version achieved a+3.88%improvement mean Average Precision(mAP)compared to the baseline PointPillars.The results demonstrate that embedding expert-based perception logic into deep neural architectures can effectively enhance performance and reduce dependency on extensive training datasets,offering a promising direction for robust 3D LiDAR object detection in real-world scenarios.展开更多
Wetting deformation in earth-rockfill dams is a critical factor influencingdam safety.Although numerous mathematical models have been developed to describe this phenomenon,most of them rely on empirical formulations a...Wetting deformation in earth-rockfill dams is a critical factor influencingdam safety.Although numerous mathematical models have been developed to describe this phenomenon,most of them rely on empirical formulations and lack prior knowledge of model parameters,which is essential for Bayesian parameter inversion to enhance accuracy and reduce uncertainty.This study introduces a datadriven approach to establishing prior knowledge of earth-rockfill dams.Driving factors are utilized to determine the potential range of model parameters,and settlement changes within this range are calculated.The results are iteratively compared with actual monitoring data until the calculated range encompasses the observed data,thereby providing prior knowledge of the model parameters.The proposed method is applied to the right-bank earth-rockfilldam of Danjiangkou.Employing a Gibbs sample size of 30,000,the proposed method effectively calibrates the prior knowledge of the wetting model parameters,achieving a root mean square error(RMSE)of 5.18 mm for the settlement predictions.By comparison,the use of non-informative priors with sample sizes of 30,000 and 50,000 results in significantly larger RMSE values of 11.97 mm and 16.07 mm,respectively.Furthermore,the computational efficiencyof the proposed method is demonstrated by an inversion computation time of 902 s for 30,000 samples,which is notably shorter than the 1026 s and 1558 s required for noninformative priors with 30,000 and 50,000 samples,respectively.These findingsunderscore the superior performance of the proposed approach in terms of both prediction accuracy and computational efficiency.These results demonstrate that the proposed method not only improves the predictive accuracy but also enhances the computational efficiency,enabling optimal parameter identificationwith reduced computational effort.This approach provides a robust and efficientframework for advancing dam safety assessments.展开更多
The viscosity of refining slags plays a critical role in metallurgical processes.However,obtaining accurate viscosity data remains challenging due to the complexities of high-temperature experiments,often relying on e...The viscosity of refining slags plays a critical role in metallurgical processes.However,obtaining accurate viscosity data remains challenging due to the complexities of high-temperature experiments,often relying on empirical models with limited predictive capabilities.This study focuses on the influence of optical basicity on viscosity in CaO-Al_(2)O_(3)-based refining slags,leveraging machine learning to address data scarcity and improve prediction accuracy.An automated framework for algorithm integration,parameter tuning,and evaluation ranking framework(Auto-APE)is employed to develop customized data-driven models for various slag systems,including CaO-Al_(2)O_(3)-SiO_(2),CaO-Al_(2)O_(3)-CaF_(2),CaO-Al_(2)O_(3)-SiO_(2)-MgO,and CaO-Al_(2)O_(3)-SiO_(2)-MgO-CaF_(2).By incorporating optical basicity as a key feature,the models achieve an average validation error of 8.0%to 15.1%,significantly outperforming traditional empirical models.Additionally,symbolic regression is introduced to rapidly construct domain-specific features,such as optical basicity-like descriptors,offering a potential breakthrough in performance prediction for small datasets.This work highlights the critical role of domain-specific knowledge in understanding and predicting viscosity,providing a robust machine learning-based approach for optimizing refining slag properties.展开更多
The reliable operation of power grid secondary equipment is an important guarantee for the safety and stability of the power system.However,various defects could be produced in the secondary equipment during longtermo...The reliable operation of power grid secondary equipment is an important guarantee for the safety and stability of the power system.However,various defects could be produced in the secondary equipment during longtermoperation.The complex relationship between the defect phenomenon andmulti-layer causes and the probabilistic influence of secondary equipment cannot be described through knowledge extraction and fusion technology by existing methods,which limits the real-time and accuracy of defect identification.Therefore,a defect recognition method based on the Bayesian network and knowledge graph fusion is proposed.The defect data of secondary equipment is transformed into the structured knowledge graph through knowledge extraction and fusion technology.The knowledge graph of power grid secondary equipment is mapped to the Bayesian network framework,combined with historical defect data,and introduced Noisy-OR nodes.The prior and conditional probabilities of the Bayesian network are then reasonably assigned to build a model that reflects the probability dependence between defect phenomena and potential causes in power grid secondary equipment.Defect identification of power grid secondary equipment is achieved by defect subgraph search based on the knowledge graph,and defect inference based on the Bayesian network.Practical application cases prove this method’s effectiveness in identifying secondary equipment defect causes,improving identification accuracy and efficiency.展开更多
To integrate traditional culture and modern technology,Shandong University’s School of Software has promoted an interdisciplinary teaching project called IYAN&ITAN,the I Ching Knowledge Graph.The project,driven b...To integrate traditional culture and modern technology,Shandong University’s School of Software has promoted an interdisciplinary teaching project called IYAN&ITAN,the I Ching Knowledge Graph.The project,driven by I Ching texts,guides students to practice natural language processing(NLP)and knowledge graph technology in a task-oriented curriculum,based on constructivism,situated learning,and inquiry-based pedagogy,with a progressive and task-oriented teaching model.The platform established enables the retrieval of knowledge,parsing of text,symbolic-numeric analysis,and historical commentary integration,making possible multidimensional,structured representation of I Ching knowledge,and offering an extensible reference for interdisciplinary learning in the context of New Engineering Education.展开更多
Objective:To assess the knowledge and attitudes of the general population regarding hepatitis B virus(HBV)infection,their association with sociodemographic factors,and the community’s willingness to pay for hepatitis...Objective:To assess the knowledge and attitudes of the general population regarding hepatitis B virus(HBV)infection,their association with sociodemographic factors,and the community’s willingness to pay for hepatitis B vaccination.Methods:This cross-sectional study was conducted from January to March 2025 in Ho Chi Minh City,Vietnam.A self-administered questionnaire was distributed to 1098 adults who were recruited via nonprobability convenience sampling.Descriptive analysis was conducted to calculate the frequencies and percentages of the categorical variables.A Chi-square test was carried out to explore the association between the independent and categorical dependent variables.Results:A total of 926 complete questionnaires were returned and included in the analysis.Among the participants,524(56.6%)exhibited good knowledge about HBV infection and vaccination,while 651(70.3%)showed positive attitudes toward the issues of interest.The factors associated with knowledge and attitudes were household incomes,health insurance,family history of HBV infection,vaccination intention,reasons for nonvaccination,sources of HBV information,and awareness of immunization programs and vaccination sites.Conclusions:Although most participants had limited knowledge of HBV symptoms and transmission,their attitudes toward vaccination remained positive.Targeted national strategies and intervention initiatives are needed since public awareness and attitudes toward the condition greatly impact intervention success.展开更多
Knowledge graphs,which combine structured representation with semantic modeling,have shown great potential in knowledge expression,causal inference,and automated reasoning,and are widely used in fields such as intelli...Knowledge graphs,which combine structured representation with semantic modeling,have shown great potential in knowledge expression,causal inference,and automated reasoning,and are widely used in fields such as intelligent question answering,decision support,and fault diagnosis.As high-speed train systems become increasingly intelligent and interconnected,fault patterns have grown more complex and dynamic.Knowledge graphs offer a promising solution to support the structured management and real-time reasoning of fault knowledge,addressing key requirements such as interpretability,accuracy,and continuous evolution in intelligent diagnostic systems.However,conventional knowledge graph construction relies heavily on domain expertise and specialized tools,resulting in high entry barriers for non-experts and limiting their practical application in frontline maintenance scenarios.To address this limitation,this paper proposes a fault knowledge modeling approach for high-speed trains that integrates structured logic diagrams with knowledge graphs.The method employs a seven-layer logic structure—comprising fault name,applicable vehicles,diagnostic logic,signal parameters,verification conditions,fault causes,and emergency measures—to transform unstructured knowledge into a visual and hierarchical representation.A semantic mapping mechanism is then used to automatically convert logic diagrams into machine-interpretable knowledge graphs,enabling dynamic reasoning and knowledge reuse.Furthermore,the proposed method establishes a three-layer architecture—logic structuring,knowledge graph transformation,and dynamic inference—to bridge human-expert logic with machinebased reasoning.Experimental validation and system implementation demonstrate that this approach not only improves knowledge interpretability and inference precision but also significantly enhances modeling efficiency and system maintainability.It provides a scalable and adaptable solution for intelligent operation and maintenance platforms in the high-speed rail domain.展开更多
Large language models(LLMs)show great potential in educational scenarios but face challenges like hallucination,knowledge gaps,and reasoning discontinuities.This study proposes a dynamic knowledge enhancement framewor...Large language models(LLMs)show great potential in educational scenarios but face challenges like hallucination,knowledge gaps,and reasoning discontinuities.This study proposes a dynamic knowledge enhancement framework.By integrating local knowledge graphs and stepwise prompting mechanisms,it improves LLMs’accuracy and interpretability in solving professional domain problems.The framework has two core modules:an LLM-driven knowledge graph construction system for incremental updates and a unified reasoning engine for generating enhanced prompts.Experiments on 680 educational questions show that the method boosts accuracy by 4.5%and 4.3%for multi-step reasoning and knowledge-dependent questions respectively,and increases reasoning step completeness from 68.2%to 83.7%.It also reduces hallucination problems.Key contributions include the followings:①validation of an effective framework synergizing knowledge graphs with retrieval mechanisms to enhance LLM reliability;②a stepwise prompting strategy enforcing explicit reasoning chain generation,addressing pedagogical requirements for process interpretability;③a lightweight deployment solution for educational systems such as adaptive learning platforms.展开更多
Aiming at the problem of insufficient recognition of implicit variants by existing Chinese sensitive text detection methods,this paper proposes the IPKE-MoE framework,which consists of three parts,namely,a sensitive w...Aiming at the problem of insufficient recognition of implicit variants by existing Chinese sensitive text detection methods,this paper proposes the IPKE-MoE framework,which consists of three parts,namely,a sensitive word variant extraction framework,a sensitive word variant knowledge enhancement layer and a mixture-of-experts(MoE)classification layer.First,sensitive word variants are precisely extracted through dynamic iterative prompt templates and the context-aware capabilities of Large Language Models(LLMs).Next,the extracted variants are used to construct a knowledge enhancement layer for sensitive word variants based on RoCBert models.Specifically,after locating variants via n-gram algorithms,variant types are mapped to embedding vectors and fused with original word vectors.Finally,a mixture-of-experts(MoE)classification layer is designed(sensitive word,sentiment,and semantic experts),which decouples the relationship between sensitiveword existence and text toxicity throughmultiple experts.This framework effectively combines the comprehension ability of Large Language Models(LLMs)with the discriminative ability of smaller models.Our two experiments demonstrate that the sensitive word variant extraction framework based on dynamically iterated prompt templates outperforms other baseline prompt templates.TheRoCBert models incorporating the sensitive word variant knowledge enhancement layer and a mixture-of-experts(MoE)classification layer achieve superior classification performance compared to other baselines.展开更多
With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or p...With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or propagation structures,with only a few recent approaches attempting causal inference;however,these have not yet effectively integrated causal discovery with domain-specific knowledge graphs for detecting health rumors.In this study,we found that the combined use of causal discovery and domain-specific knowledge graphs can effectively identify implicit pseudo-causal logic embedded within texts,holding significant potential for health rumor detection.To this end,we propose CKDG—a dual-graph fusion framework based on causal logic and medical knowledge graphs.CKDG constructs a weighted causal graph to capture the implicit causal relationships in the text and introduces a medical knowledge graph to verify semantic consistency,thereby enhancing the ability to identify the misuse of professional terminology and pseudoscientific claims.In experiments conducted on a dataset comprising 8430 health rumors,CKDG achieved an accuracy of 91.28%and an F1 score of 90.38%,representing improvements of 5.11%and 3.29%over the best baseline,respectively.Our results indicate that the integrated use of causal discovery and domainspecific knowledge graphs offers significant advantages for health rumor detection systems.This method not only improves detection performance but also enhances the transparency and credibility of model decisions by tracing causal chains and sources of knowledge conflicts.We anticipate that this work will provide key technological support for the development of trustworthy health-information filtering systems,thereby improving the reliability of public health information on social media.展开更多
Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Re...Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.展开更多
文摘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.
基金Supported by National Key Research and Development Program(Grant No.2024YFB3312700)National Natural Science Foundation of China(Grant No.52405541)the Changzhou Municipal Sci&Tech Program(Grant No.CJ20241131)。
文摘Under the paradigm of Industry 5.0,intelligent manufacturing transcends mere efficiency enhancement by emphasizing human-machine collaboration,where human expertise plays a central role in assembly processes.Despite advancements in intelligent and digital technologies,assembly process design still heavily relies on manual knowledge reuse,and inefficiencies and inconsistent quality in process documentation are caused.To address the aforementioned issues,this paper proposes a knowledge push method of complex product assembly process design based on distillation model-based dynamically enhanced graph and Bayesian network.First,an initial knowledge graph is constructed using a BERT-BiLSTM-CRF model trained with integrated human expertise and a fine-tuned large language model.Then,a confidence-based dynamic weighted fusion strategy is employed to achieve dynamic incremental construction of the knowledge graph with low resource consumption.Subsequently,a Bayesian network model is constructed based on the relationships between assembly components,assembly features,and operations.Bayesian network reasoning is used to push assembly process knowledge under different design requirements.Finally,the feasibility of the Bayesian network construction method and the effectiveness of Bayesian network reasoning are verified through a specific example,significantly improving the utilization of assembly process knowledge and the efficiency of assembly process design.
文摘Water scarcity poses a significant challenge globally,with South Africa exemplifying the severe socio-economic and environmental impacts of limited water access.Despite advances in modern water management systems,the integration of indigenous knowledge(IK)into formal frameworks remains underutilized.This study systematically reviews the role of indigenous water conservation practices in South Africa,analyzing over 50 high-quality sources using the PRISMA methodology.The findings highlight the effectiveness of IK in addressing water scarcity through techniques such as rainwater harvesting,terracing,and wetland management,which are low-cost,environmentally sustainable,and deeply rooted in cultural practices.Indigenous methods also enhance climate resilience by enabling communities to adapt to droughts and floods through practices such as weather prediction and adaptive farming techniques.Furthermore,these practices foster social inclusivity and community empowerment,ensuring equitable water access and intergenerational knowledge transfer.The study underscores the potential of integrating IK with modern water technologies to create holistic solutions that are scalable,sustainable,and aligned with South Africa’s goal of achieving water security by 2030.Policy recommendations emphasize the need for institutional support,data collection,and financial incentives to sustain and mainstream indigenous approaches.By bridging the gap between traditional and contemporary systems,this research provides a roadmap for leveraging diverse knowledge systems to address water scarcity and build resilient communities.
文摘Xi Jinping,general secretary of the Communist Party of China(CPC)Central Committee,stressed that we should adhere to the“two integrations”(namely,integrating the basic tenets of Marxism with China’s specific realities and fine traditional culture),root ourselves in Chinese soil,carry forward the Chinese cultural heritage,and strengthen the academic foundation.We should accelerate the building of an independent knowledge system for Chinese philosophy and social sciences,and formulate original concepts and develop systems of academic discipline,research and discourse,drawing on China’s rich experience of advancing human rights.In the face of changes of a magnitude not seen in a century,in the historic process of advancing the great rejuvenation of the Chinese nation on all fronts through Chinese modernization,we should and must strengthen our theoretical self-consciousness and confidence in the path of Chinese modernization.We need to enhance human rights research,develop the human rights theoretical system and paradigm that are based on Chinese realities and express Chinese voice,and an independent Chinese knowledge system for human rights.
基金supported by the Innovation Fund for Medical Sciences of the Chinese Academy of Medical Sciences(2021-I2M-1-033)the National Key Research and Development Program of China(2022YFF0711900).
文摘Recent advancements in large language models(LLMs)have driven remarkable progress in text process-ing,opening new avenues for medical knowledge discovery.In this study,we present ERQA,a mEdical knowledge Retrieval and Question-Answering framework powered by an enhanced LLM that integrates a semantic vector database and a curated literature repository.The ERQA framework leverages domain-specific incremental pretraining and conducts supervised fine-tuning on medical literature,enabling retrieval and question-answering(QA)tasks to be completed with high precision.Performance evaluations implemented on the coronavirus disease 2019(COVID-19)and TripClick data-sets demonstrate the robust capabilities of ERQA across multiple tasks.On the COVID-19 dataset,ERQA-13B achieves state-of-the-art retrieval metrics,with normalized discounted cumulative gain at top 10(NDCG@10)0.297,recall values at top 10(Recall@10)0.347,and mean reciprocal rank(MRR)=0.370;it also attains strong abstract summarization performance,with a recall-oriented understudy for gisting evaluation(ROUGE)-1 score of 0.434,and QA performance,with a bilingual evaluation understudy(BLEU)-1 score of 7.851.The comparable performance achieved on the TripClick dataset further under-scores the adaptability of ERQA across diverse medical topics.These findings suggest that ERQA repre-sents a significant step toward efficient biomedical knowledge retrieval and QA.
基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDA26050301-02)。
文摘The global rise in animal protein consumption has significantly amplified the demand for fodder.A comprehensive understanding of the diversity and characteristics of existing fodder resources is essential for balanced nutritional fodder production.This study investigates the diversity and composition of fodder plants and identifies key species for cattle in Zhaotong City,Yunnan,China,while documenting indigenous knowledge on their usage and selection criteria.Ethnobotanical surveys were conducted in 19 villages across seven townships with 140 informants.Data were collected through semi-structured interviews,free listing,and participatory observation,and analyzed using Relative Frequency Citation.A total of 125 taxa(including 106 wild and 19 cultivated)were reported.The most cited family is Poaceae(27 taxa,21.43%),followed by Asteraceae(17 taxa,13.49%),Fabaceae(14 taxa,11.11%),Polygonaceae(9 taxa,7.14%)and Lamiaceae(4 taxa,3.17%).The whole plant(66.04%)and herbaceous plants(84.80%)were the most used parts and life forms.The most cited species were Zea mays,Brassica rapa,Solanum tuberosum,Eragrostis nigra,and Artemisia dubia.Usage of diverse fodder resources reflects local wisdom in managing resource availability and achieving balanced nutrition while coping with environmental and climatic risks.Preferences for certain taxonomic groups are due to their quality as premier fodder resources.To promote integrated crop-livestock farming,we suggest further research into highly preferred fodder species,focusing on nutritional assessment,digestibility,meat quality impacts,and potential as antibiotic alternatives.Establishing germplasm and gene banks for fodder resources is also recommended.
文摘Since Google introduced the concept of Knowledge Graphs(KGs)in 2012,their construction technologies have evolved into a comprehensive methodological framework encompassing knowledge acquisition,extraction,representation,modeling,fusion,computation,and storage.Within this framework,knowledge extraction,as the core component,directly determines KG quality.In military domains,traditional manual curation models face efficiency constraints due to data fragmentation,complex knowledge architectures,and confidentiality protocols.Meanwhile,crowdsourced ontology construction approaches from general domains prove non-transferable,while human-crafted ontologies struggle with generalization deficiencies.To address these challenges,this study proposes an OntologyAware LLM Methodology for Military Domain Knowledge Extraction(LLM-KE).This approach leverages the deep semantic comprehension capabilities of Large Language Models(LLMs)to simulate human experts’cognitive processes in crowdsourced ontology construction,enabling automated extraction of military textual knowledge.It concurrently enhances knowledge processing efficiency and improves KG completeness.Empirical analysis demonstrates that this method effectively resolves scalability and dynamic adaptation challenges in military KG construction,establishing a novel technological pathway for advancing military intelligence development.
基金supported by the National Natural Science Foundation of China(No.62267005)the Chinese Guangxi Natural Science Foundation(No.2023GXNSFAA026493)+1 种基金Guangxi Collaborative Innovation Center ofMulti-Source Information Integration and Intelligent ProcessingGuangxi Academy of Artificial Intelligence.
文摘The rapid development of information technology and accelerated digitalization have led to an explosive growth of data across various fields.As a key technology for knowledge representation and sharing,knowledge graphs play a crucial role by constructing structured networks of relationships among entities.However,data sparsity and numerous unexplored implicit relations result in the widespread incompleteness of knowledge graphs.In static knowledge graph completion,most existing methods rely on linear operations or simple interaction mechanisms for triple encoding,making it difficult to fully capture the deep semantic associations between entities and relations.Moreover,many methods focus only on the local information of individual triples,ignoring the rich semantic dependencies embedded in the neighboring nodes of entities within the graph structure,which leads to incomplete embedding representations.To address these challenges,we propose Two-Stage Mixer Embedding(TSMixerE),a static knowledge graph completion method based on entity context.In the unit semantic extraction stage,TSMixerE leveragesmulti-scale circular convolution to capture local features atmultiple granularities,enhancing the flexibility and robustness of feature interactions.A channel attention mechanism amplifies key channel responses to suppress noise and irrelevant information,thereby improving the discriminative power and semantic depth of feature representations.For contextual information fusion,a multi-layer self-attentionmechanism enables deep interactions among contextual cues,effectively integrating local details with global context.Simultaneously,type embeddings clarify the semantic identities and roles of each component,enhancing the model’s sensitivity and fusion capabilities for diverse information sources.Furthermore,TSMixerE constructs contextual unit sequences for entities,fully exploring neighborhood information within the graph structure to model complex semantic dependencies,thus improving the completeness and generalization of embedding representations.
基金supported by Harbin Institute of Technology High-level Teaching Achievement Award(National Level)Cultivation Project(256709).
文摘This paper delves into effective pathways for transforming course ecosystems from resource provision to knowledge service and competency development through university-enterprise collaboration in co-building knowledge graphs and intelligent shared courses.This approach enables personalized,learning-driven teaching.Based on knowledge graphs and integrated teacher-machine-student smart teaching scenarios,it not only innovates autonomous learning environments and human-computer interaction models while optimizing teaching experiences for both instructors and students,but also effectively addresses the issues of students’“scattered,superficial,and fragmented learning”.This establishes the foundation for personalized teaching tailored to individual aptitudes.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2023-00245084)by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(RS-2024-00415938,HRD Program for Industrial Innovation)and Soonchunhyang University.
文摘This paper proposes a deep learning-based 3D LiDAR perception framework designed for applications such as autonomous robots and vehicles.To address the high dependency on large-scale annotated data—an inherent limitation of deep learning models—this study introduces a hybrid perception architecture that incorporates expertdriven LiDAR processing techniques into the deep neural network.Traditional 3DLiDAR processingmethods typically remove ground planes and apply distance-or density-based clustering for object detection.In this work,such expert knowledge is encoded as feature-level inputs and fused with the deep network,therebymitigating the data dependency issue of conventional learning-based approaches.Specifically,the proposedmethod combines two expert algorithms—Patchwork++for ground segmentation and DBSCAN for clustering—with a PointPillars-based LiDAR detection network.We design four hybrid versions of the network depending on the stage and method of integrating expert features into the feature map of the deep model.Among these,Version 4 incorporates a modified neck structure in PointPillars and introduces a new Cluster 2D Pseudo-Map Branch that utilizes cluster-level pseudo-images generated from Patchwork++and DBSCAN.This version achieved a+3.88%improvement mean Average Precision(mAP)compared to the baseline PointPillars.The results demonstrate that embedding expert-based perception logic into deep neural architectures can effectively enhance performance and reduce dependency on extensive training datasets,offering a promising direction for robust 3D LiDAR object detection in real-world scenarios.
基金supported by the National Key R&D Program of China(Grant No.2023YFC3209504)Natural Science Foundation of Wuhan(Grant No.2024040801020271)the Fundamental Research Funds for Central Public Welfare Research Institutes(Grant No.CKSF2025718/YT).
文摘Wetting deformation in earth-rockfill dams is a critical factor influencingdam safety.Although numerous mathematical models have been developed to describe this phenomenon,most of them rely on empirical formulations and lack prior knowledge of model parameters,which is essential for Bayesian parameter inversion to enhance accuracy and reduce uncertainty.This study introduces a datadriven approach to establishing prior knowledge of earth-rockfill dams.Driving factors are utilized to determine the potential range of model parameters,and settlement changes within this range are calculated.The results are iteratively compared with actual monitoring data until the calculated range encompasses the observed data,thereby providing prior knowledge of the model parameters.The proposed method is applied to the right-bank earth-rockfilldam of Danjiangkou.Employing a Gibbs sample size of 30,000,the proposed method effectively calibrates the prior knowledge of the wetting model parameters,achieving a root mean square error(RMSE)of 5.18 mm for the settlement predictions.By comparison,the use of non-informative priors with sample sizes of 30,000 and 50,000 results in significantly larger RMSE values of 11.97 mm and 16.07 mm,respectively.Furthermore,the computational efficiencyof the proposed method is demonstrated by an inversion computation time of 902 s for 30,000 samples,which is notably shorter than the 1026 s and 1558 s required for noninformative priors with 30,000 and 50,000 samples,respectively.These findingsunderscore the superior performance of the proposed approach in terms of both prediction accuracy and computational efficiency.These results demonstrate that the proposed method not only improves the predictive accuracy but also enhances the computational efficiency,enabling optimal parameter identificationwith reduced computational effort.This approach provides a robust and efficientframework for advancing dam safety assessments.
基金supported by the National Key Research and Development Program of China(No.2023YFB3712401),the National Natural Science Foundation of China(No.52274301)the Aeronautical Science Foundation of China(No.2023Z0530S6005)the Ningbo Yongjiang Talent-Introduction Programme(No.2022A-023-C).
文摘The viscosity of refining slags plays a critical role in metallurgical processes.However,obtaining accurate viscosity data remains challenging due to the complexities of high-temperature experiments,often relying on empirical models with limited predictive capabilities.This study focuses on the influence of optical basicity on viscosity in CaO-Al_(2)O_(3)-based refining slags,leveraging machine learning to address data scarcity and improve prediction accuracy.An automated framework for algorithm integration,parameter tuning,and evaluation ranking framework(Auto-APE)is employed to develop customized data-driven models for various slag systems,including CaO-Al_(2)O_(3)-SiO_(2),CaO-Al_(2)O_(3)-CaF_(2),CaO-Al_(2)O_(3)-SiO_(2)-MgO,and CaO-Al_(2)O_(3)-SiO_(2)-MgO-CaF_(2).By incorporating optical basicity as a key feature,the models achieve an average validation error of 8.0%to 15.1%,significantly outperforming traditional empirical models.Additionally,symbolic regression is introduced to rapidly construct domain-specific features,such as optical basicity-like descriptors,offering a potential breakthrough in performance prediction for small datasets.This work highlights the critical role of domain-specific knowledge in understanding and predicting viscosity,providing a robust machine learning-based approach for optimizing refining slag properties.
基金supported by the State Grid Southwest Branch Project“Research on Defect Diagnosis and Early Warning Technology of Relay Protection and Safety Automation Devices Based on Multi-Source Heterogeneous Defect Data”.
文摘The reliable operation of power grid secondary equipment is an important guarantee for the safety and stability of the power system.However,various defects could be produced in the secondary equipment during longtermoperation.The complex relationship between the defect phenomenon andmulti-layer causes and the probabilistic influence of secondary equipment cannot be described through knowledge extraction and fusion technology by existing methods,which limits the real-time and accuracy of defect identification.Therefore,a defect recognition method based on the Bayesian network and knowledge graph fusion is proposed.The defect data of secondary equipment is transformed into the structured knowledge graph through knowledge extraction and fusion technology.The knowledge graph of power grid secondary equipment is mapped to the Bayesian network framework,combined with historical defect data,and introduced Noisy-OR nodes.The prior and conditional probabilities of the Bayesian network are then reasonably assigned to build a model that reflects the probability dependence between defect phenomena and potential causes in power grid secondary equipment.Defect identification of power grid secondary equipment is achieved by defect subgraph search based on the knowledge graph,and defect inference based on the Bayesian network.Practical application cases prove this method’s effectiveness in identifying secondary equipment defect causes,improving identification accuracy and efficiency.
基金support provided by the Shandong University Education and Teaching Reform Research Project(2024Y232)the“New 20 Regulations for Universities”funding program of Jinan(202228089).
文摘To integrate traditional culture and modern technology,Shandong University’s School of Software has promoted an interdisciplinary teaching project called IYAN&ITAN,the I Ching Knowledge Graph.The project,driven by I Ching texts,guides students to practice natural language processing(NLP)and knowledge graph technology in a task-oriented curriculum,based on constructivism,situated learning,and inquiry-based pedagogy,with a progressive and task-oriented teaching model.The platform established enables the retrieval of knowledge,parsing of text,symbolic-numeric analysis,and historical commentary integration,making possible multidimensional,structured representation of I Ching knowledge,and offering an extensible reference for interdisciplinary learning in the context of New Engineering Education.
基金funded by Vietnam National University Ho Chi Minh City(VNU-HCM)under grant number 36-2025-44-02.
文摘Objective:To assess the knowledge and attitudes of the general population regarding hepatitis B virus(HBV)infection,their association with sociodemographic factors,and the community’s willingness to pay for hepatitis B vaccination.Methods:This cross-sectional study was conducted from January to March 2025 in Ho Chi Minh City,Vietnam.A self-administered questionnaire was distributed to 1098 adults who were recruited via nonprobability convenience sampling.Descriptive analysis was conducted to calculate the frequencies and percentages of the categorical variables.A Chi-square test was carried out to explore the association between the independent and categorical dependent variables.Results:A total of 926 complete questionnaires were returned and included in the analysis.Among the participants,524(56.6%)exhibited good knowledge about HBV infection and vaccination,while 651(70.3%)showed positive attitudes toward the issues of interest.The factors associated with knowledge and attitudes were household incomes,health insurance,family history of HBV infection,vaccination intention,reasons for nonvaccination,sources of HBV information,and awareness of immunization programs and vaccination sites.Conclusions:Although most participants had limited knowledge of HBV symptoms and transmission,their attitudes toward vaccination remained positive.Targeted national strategies and intervention initiatives are needed since public awareness and attitudes toward the condition greatly impact intervention success.
基金support from the Scientific Funding for the Center of National Railway Intelligent Transportation System Engineering and Technology,China Academy of Railway Sciences Corporation Limited(Grant No.2023YJ354)。
文摘Knowledge graphs,which combine structured representation with semantic modeling,have shown great potential in knowledge expression,causal inference,and automated reasoning,and are widely used in fields such as intelligent question answering,decision support,and fault diagnosis.As high-speed train systems become increasingly intelligent and interconnected,fault patterns have grown more complex and dynamic.Knowledge graphs offer a promising solution to support the structured management and real-time reasoning of fault knowledge,addressing key requirements such as interpretability,accuracy,and continuous evolution in intelligent diagnostic systems.However,conventional knowledge graph construction relies heavily on domain expertise and specialized tools,resulting in high entry barriers for non-experts and limiting their practical application in frontline maintenance scenarios.To address this limitation,this paper proposes a fault knowledge modeling approach for high-speed trains that integrates structured logic diagrams with knowledge graphs.The method employs a seven-layer logic structure—comprising fault name,applicable vehicles,diagnostic logic,signal parameters,verification conditions,fault causes,and emergency measures—to transform unstructured knowledge into a visual and hierarchical representation.A semantic mapping mechanism is then used to automatically convert logic diagrams into machine-interpretable knowledge graphs,enabling dynamic reasoning and knowledge reuse.Furthermore,the proposed method establishes a three-layer architecture—logic structuring,knowledge graph transformation,and dynamic inference—to bridge human-expert logic with machinebased reasoning.Experimental validation and system implementation demonstrate that this approach not only improves knowledge interpretability and inference precision but also significantly enhances modeling efficiency and system maintainability.It provides a scalable and adaptable solution for intelligent operation and maintenance platforms in the high-speed rail domain.
基金supported in part by the China-Singapore International Joint Research Institute(CSIJRI)under Grant No.206-A023001the Undergraduate Teaching Reform Project of Shandong University under Grant Nos.2023Y235 and 2025Y99.
文摘Large language models(LLMs)show great potential in educational scenarios but face challenges like hallucination,knowledge gaps,and reasoning discontinuities.This study proposes a dynamic knowledge enhancement framework.By integrating local knowledge graphs and stepwise prompting mechanisms,it improves LLMs’accuracy and interpretability in solving professional domain problems.The framework has two core modules:an LLM-driven knowledge graph construction system for incremental updates and a unified reasoning engine for generating enhanced prompts.Experiments on 680 educational questions show that the method boosts accuracy by 4.5%and 4.3%for multi-step reasoning and knowledge-dependent questions respectively,and increases reasoning step completeness from 68.2%to 83.7%.It also reduces hallucination problems.Key contributions include the followings:①validation of an effective framework synergizing knowledge graphs with retrieval mechanisms to enhance LLM reliability;②a stepwise prompting strategy enforcing explicit reasoning chain generation,addressing pedagogical requirements for process interpretability;③a lightweight deployment solution for educational systems such as adaptive learning platforms.
基金funded by the National Natural Science Foundation of China(Grant No.62441212)the Major Project of the Natural Science Foundation of Inner Mongolia(Grant No.2025ZD008).
文摘Aiming at the problem of insufficient recognition of implicit variants by existing Chinese sensitive text detection methods,this paper proposes the IPKE-MoE framework,which consists of three parts,namely,a sensitive word variant extraction framework,a sensitive word variant knowledge enhancement layer and a mixture-of-experts(MoE)classification layer.First,sensitive word variants are precisely extracted through dynamic iterative prompt templates and the context-aware capabilities of Large Language Models(LLMs).Next,the extracted variants are used to construct a knowledge enhancement layer for sensitive word variants based on RoCBert models.Specifically,after locating variants via n-gram algorithms,variant types are mapped to embedding vectors and fused with original word vectors.Finally,a mixture-of-experts(MoE)classification layer is designed(sensitive word,sentiment,and semantic experts),which decouples the relationship between sensitiveword existence and text toxicity throughmultiple experts.This framework effectively combines the comprehension ability of Large Language Models(LLMs)with the discriminative ability of smaller models.Our two experiments demonstrate that the sensitive word variant extraction framework based on dynamically iterated prompt templates outperforms other baseline prompt templates.TheRoCBert models incorporating the sensitive word variant knowledge enhancement layer and a mixture-of-experts(MoE)classification layer achieve superior classification performance compared to other baselines.
基金funded by the Hunan Provincial Natural Science Foundation of China(Grant No.2025JJ70105)the Hunan Provincial College Students’Innovation and Entrepreneurship Training Program(Project No.S202411342056)The article processing charge(APC)was funded by the Project No.2025JJ70105.
文摘With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or propagation structures,with only a few recent approaches attempting causal inference;however,these have not yet effectively integrated causal discovery with domain-specific knowledge graphs for detecting health rumors.In this study,we found that the combined use of causal discovery and domain-specific knowledge graphs can effectively identify implicit pseudo-causal logic embedded within texts,holding significant potential for health rumor detection.To this end,we propose CKDG—a dual-graph fusion framework based on causal logic and medical knowledge graphs.CKDG constructs a weighted causal graph to capture the implicit causal relationships in the text and introduces a medical knowledge graph to verify semantic consistency,thereby enhancing the ability to identify the misuse of professional terminology and pseudoscientific claims.In experiments conducted on a dataset comprising 8430 health rumors,CKDG achieved an accuracy of 91.28%and an F1 score of 90.38%,representing improvements of 5.11%and 3.29%over the best baseline,respectively.Our results indicate that the integrated use of causal discovery and domainspecific knowledge graphs offers significant advantages for health rumor detection systems.This method not only improves detection performance but also enhances the transparency and credibility of model decisions by tracing causal chains and sources of knowledge conflicts.We anticipate that this work will provide key technological support for the development of trustworthy health-information filtering systems,thereby improving the reliability of public health information on social media.
文摘Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.
