In this paper it is emphasized that human language has two rather different dimensions corresponding to two different language systems: lexical/semantic and grammatical. These two language systems are supported by dif...In this paper it is emphasized that human language has two rather different dimensions corresponding to two different language systems: lexical/semantic and grammatical. These two language systems are supported by different brain structures (temporal and frontal), and based in different learning strategies (declarative and procedural). In cases of brain pathology, each one can be independently impaired (Wernicke aphasia and Broca aphasia). While the lexical/semantic language system may have appeared during human evolution long before the contemporary man, the grammatical language system probably represents a relatively recent acquisition. Language grammar may be the departing ability for the development of the metacognitive executive functions and is probably based in the ability to internally represent actions.展开更多
This essay elaborates as thoroughly as possible the theory of internal compensation of the natural language system, and proves that the general distinctive function, which vanishes because of the loss or decrease of o...This essay elaborates as thoroughly as possible the theory of internal compensation of the natural language system, and proves that the general distinctive function, which vanishes because of the loss or decrease of one or more sub-systems or units with their distinctive function, will be compensated with the increase of others or something new to guarantee the general balance of the whole system and fulfill the need of communication. By just discussing some phenomena of internal compensation at the phonological level here, this essay reveals some interesting rules and gives new explanations to some phenomena that have not been explained or not explained properly, then prove the theory’s function of explanation.展开更多
Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interact...Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.展开更多
Background:Foreign Language Anxiety(FLA)represents a substantial affective barrier that undermines cognitive performance,motivation,and retention in language learners.Emerging evidence highlights mindfulness-based int...Background:Foreign Language Anxiety(FLA)represents a substantial affective barrier that undermines cognitive performance,motivation,and retention in language learners.Emerging evidence highlights mindfulness-based interventions as promising strategies for enhancing emotional regulation and reducing anxiety across educational contexts.This review synthesizes current research on mindfulness as a psychological intervention,aims to evaluate its efficacy in alleviating FLA,and discusses its broader implications for health-focused educational policy and practice.Methods:Following PRISMA guidelines,we systematically reviewed studies examining the relationships between mindfulness and FLA.Our search of four major databases(November 2023)initially identified 346 articles using terms like“mindfulness AND language anxiety.”After screening,14 studies met our criteria:(1)empirical research in English on mindfulness-FLA relationships;(2)no publication date restrictions.Two independent reviewers selected studies,excluding two due to methodological limitations.We conducted a narrative synthesis given the study heterogeneity(9 correlational and 5 intervention studies).Results:9 non-intervention studies demonstrated that mindfulness is negatively associated with FLA,with 3 studies highlighting the mediating roles of self-efficacy and resilience.5 intervention studies reported inconsistent results regarding the efficacy of mindfulness-based interventions in reducing FLA.Conclusions:The findings suggest that while mindfulness holds promise as a tool to address FLA,its mechanisms and effectiveness require further investigation.This study underscores the need for rigorous research,including Randomized Controlled Trials(RCTs),to inform evidence-based integration of mindfulness into foreign language curricula.For educational policymakers and practitioners,these insights highlight the importance of adopting mindfulness interventions cautiously,ensuring they are tailored to students’needs and supported by evidence.展开更多
Anxiety,motivation,and strategy have long been seen as critical in second language acquisition.This study presents a systematic review of the literature on these variables in terms of their relationship with one anoth...Anxiety,motivation,and strategy have long been seen as critical in second language acquisition.This study presents a systematic review of the literature on these variables in terms of their relationship with one another,their effects on learning outcomes,and how they are affected by technology-assisted tools in the teaching of Chinese as a second language.This study includes 24 articles for the review study based on the criteria and process of the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocol(PRISMA-P)and the clustering techniques of VOSviewer.It is found that 1)anxiety,motivation,and strategy were interrelated,that is,motivation was negatively associated with anxiety but positively related to strategy,while strategy could positively predict anxiety;2)anxiety could both positively and negatively affect learning outcomes,while motivation and strategy could both positively and insignificantly influence learning outcomes;3)the technology-assisted tools used in the classroom could both positively and negatively affect the levels of these variables and learning outcomes in the L2 Chinese context.The need to explore more complicated relationships between language-specific individual variables themselves and other possible factors that affect these variables,such as cultural ones,are also discussed for future research.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
Objective:Generative artificial intelligence(AI)technology,represented by large language models(LLMs),has gradually been developed for traditional Chinese medicine(TCM);however,challenges remain in effectively enhanci...Objective:Generative artificial intelligence(AI)technology,represented by large language models(LLMs),has gradually been developed for traditional Chinese medicine(TCM);however,challenges remain in effectively enhancing AI applications for TCM.Therefore,this study is the first systematic review to analyze LLMs in TCM retrospectively,focusing on and summarizing the evidence of their performance in generative tasks.Methods:We extensively searched electronic databases for articles published until June 2024 to identify publicly available studies on LLMs in TCM.Two investigators independently selected and extracted the related information and evaluation metrics.Based on the available data,this study used descriptive analysis for a comprehensive systematic review of LLM technology related to TCM.Results:Ten studies published between 2023 and 2024 met our eligibility criteria and were included in this review,including 40%LLMs in the TCM vertical domain,40%containing TCM data,and 20%honoring the TCM contribution,with a foundational model parameter range from 1.8 to 33 billion.All included studies used manual or automatic evaluation metrics to evaluate model performance and fully discussed the challenges and contributions through an overview of LLMs in TCM.Conclusions:LLMs have achieved significant advantages in TCM applications and can effectively address intelligent TCM tasks.Further in-depth development of LLMs is needed in various vertical TCM fields,including clinical and fundamental research.Focusing on the functional segmentation development direction of generative AI technologies in TCM application scenarios to meet the practical needs-oriented demands of TCM digitalization is essential.展开更多
In the era of big data,data-driven technologies are increasingly leveraged by industry to facilitate autonomous learning and intelligent decision-making.However,the challenge of“small samples in big data”emerges whe...In the era of big data,data-driven technologies are increasingly leveraged by industry to facilitate autonomous learning and intelligent decision-making.However,the challenge of“small samples in big data”emerges when datasets lack the comprehensive information necessary for addressing complex scenarios,which hampers adaptability.Thus,enhancing data completeness is essential.Knowledge-guided virtual sample generation transforms domain knowledge into extensive virtual datasets,thereby reducing dependence on limited real samples and enabling zero-sample fault diagnosis.This study used building air conditioning systems as a case study.We innovatively used the large language model(LLM)to acquire domain knowledge for sample generation,significantly lowering knowledge acquisition costs and establishing a generalized framework for knowledge acquisition in engineering applications.This acquired knowledge guided the design of diffusion boundaries in mega-trend diffusion(MTD),while the Monte Carlo method was used to sample within the diffusion function to create information-rich virtual samples.Additionally,a noise-adding technique was introduced to enhance the information entropy of these samples,thereby improving the robustness of neural networks trained with them.Experimental results showed that training the diagnostic model exclusively with virtual samples achieved an accuracy of 72.80%,significantly surpassing traditional small-sample supervised learning in terms of generalization.This underscores the quality and completeness of the generated virtual samples.展开更多
Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLM...Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.展开更多
Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remain...Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remains one of the security challenges. is paper proposes LinguTimeX,a new framework that combines natural language processing with arti cial intelligence,along with explainable Arti cial Intelligence(AI)not only to detect CTC but also to provide insights into the decision process.LinguTimeX performs multidimensional feature extraction by fusing linguistic attributes with temporal network patterns to identify covert channels precisely.LinguTimeX demonstrates strong e ectiveness in detecting CTC across multiple languages;namely English,Arabic,and Chinese.Speci cally,the LSTM and RNN models achieved F1 scores of 90%on the English dataset,89%on the Arabic dataset,and 88%on the Chinese dataset,showcasing their superior performance and ability to generalize across multiple languages. is highlights their robustness in detecting CTCs within security systems,regardless of the language or cultural context of the data.In contrast,the DeepForest model produced F1-scores ranging from 86%to 87%across the same datasets,further con rming its e ectiveness in CTC detection.Although other algorithms also showed reasonable accuracy,the LSTM and RNN models consistently outperformed them in multilingual settings,suggesting that deep learning models might be better suited for this particular problem.展开更多
The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in S...The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.展开更多
This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to use...This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.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
The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness dimin...The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.展开更多
Background:In mental health,recovery is emphasized,and qualitative analyses of service users’narratives have accumulated;however,while qualitative approaches excel at capturing rich context and generating new concept...Background:In mental health,recovery is emphasized,and qualitative analyses of service users’narratives have accumulated;however,while qualitative approaches excel at capturing rich context and generating new concepts,they are limited in generalizability and feasible data volume.This study aimed to quantify the subjective life history narratives of users of psychiatric home-visit nursing using natural language processing(NLP)and to clarify the relationships between linguistic features and recovery-related indicators.Methods:We conducted audio-recorded and transcribed semi-structured interviews on daily life verbatim and collected self-report questionnaires(Recovery Assessment Scale[RAS])and clinician ratings(Global Assessment of Functioning[GAF])from Japanese users of psychiatric home-visit nursing.Using the artificial intelligence-based topic-modeling method BERTopic,we extracted topics from the interview texts and calculated each participant’s topic proportions,and then examined associations between topic proportions and recovery-related indicators using Pearson correlation analyses.Results:“School”showed a significant positive correlation with RAS(r=0.39,p=0.05),whereas“Family”showed a significant negative correlation(r=–0.46,p=0.02).GAF was positively correlated with word count(r=0.44,p=0.02)and“Hospital”(r=0.42,p=0.03),and negatively correlated with“Backchannels”(aizuchi)(r=–0.41,p=0.03).Conclusion:The present results suggest that the quantity,quality,and content of narratives can serve as useful indicators of mental health and recovery,and that objective NLP-based analysis of service users’narratives can complement traditional self-report scales and clinician ratings to inform the design of recovery-oriented care in psychiatric home-visit nursing.展开更多
War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient an...War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.展开更多
This interview examines the theoretical foundations,pedagogical applications,developmental trajectory,and future directions of the xu-argument.Professor Wang Chuming offers a comprehensive account of the xu-argument,c...This interview examines the theoretical foundations,pedagogical applications,developmental trajectory,and future directions of the xu-argument.Professor Wang Chuming offers a comprehensive account of the xu-argument,clarifying its theoretical framework,the learning mechanisms underlying xu,and its interface with international theories of second language acquisition(SLA).From the perspective of the xu-argument,he proposes novel interpretations of core issues in SLA.Drawing on the development of the xu-argument,Wang further discusses the essence,directions,and methodology of innovation in SLA theory.He emphasizes that theoretical advances must capture and illuminate underlying natural laws,arguing that innovative approaches are typically rooted in deep reflection on common sense.He also calls for theoretical innovation in SLA in the Chinese context,advocating a robust research paradigm that shifts from local observation to global theoretical generalization,thereby promoting bottom-up theoretical development.In closing,he highlights the promising prospects for SLA theory in the era of artificial intelligence.展开更多
Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that man...Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.展开更多
Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lack...Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lacks formal task definitions and corresponding benchmarks.To bridge this gap,we define the Automated Online Public Opinion Report Generation(OPOR-Gen)task and construct OPOR-Bench,an event-centric dataset with 463 crisis events across 108 countries(comprising 8.8 K news articles and 185 K tweets).To evaluate report quality,we propose OPOR-Eval,a novel agent-based framework that simulates human expert evaluation.Validation experiments show OPOR-Eval achieves a high Spearman’s correlation(ρ=0.70)with human judgments,though challenges in temporal reasoning persist.This work establishes an initial foundation for advancing automated public opinion reporting research.展开更多
This paper undertakes a systematic combing of the development of research on integrating Chinese culture into foreign language education in China from the 1980s to 2025,dividing it into three stages:cultural attachmen...This paper undertakes a systematic combing of the development of research on integrating Chinese culture into foreign language education in China from the 1980s to 2025,dividing it into three stages:cultural attachment,cultural compensation,and cultural symbiosis,and reveals the logical shift of the research from the dominance of target language culture to the construction of the subjectivity of Chinese culture.Through quantitative and qualitative analysis of 435 CSSCI papers,three core themes are extracted:what to integrate,why to integrate,and how to integrate.This paper critically analyzes three pairs of contradictions:the imbalance between instrumentality and humanism,the separation of national narrative and individual expression,and the disconnection between traditional inheritance and modern transformation.It is proposed that future research should reconstruct the educational logic based on the Chinese context,integrate the national and individual dimensions,and build a dialogue mechanism between tradition and modernity,so as to provide theoretical and practical reference for the construction of a foreign language education system with Chinese characteristics.展开更多
文摘In this paper it is emphasized that human language has two rather different dimensions corresponding to two different language systems: lexical/semantic and grammatical. These two language systems are supported by different brain structures (temporal and frontal), and based in different learning strategies (declarative and procedural). In cases of brain pathology, each one can be independently impaired (Wernicke aphasia and Broca aphasia). While the lexical/semantic language system may have appeared during human evolution long before the contemporary man, the grammatical language system probably represents a relatively recent acquisition. Language grammar may be the departing ability for the development of the metacognitive executive functions and is probably based in the ability to internally represent actions.
文摘This essay elaborates as thoroughly as possible the theory of internal compensation of the natural language system, and proves that the general distinctive function, which vanishes because of the loss or decrease of one or more sub-systems or units with their distinctive function, will be compensated with the increase of others or something new to guarantee the general balance of the whole system and fulfill the need of communication. By just discussing some phenomena of internal compensation at the phonological level here, this essay reveals some interesting rules and gives new explanations to some phenomena that have not been explained or not explained properly, then prove the theory’s function of explanation.
基金supported by the National Key R&D Program of China[2022YFF0902703]the State Administration for Market Regulation Science and Technology Plan Project(2024MK033).
文摘Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.
文摘Background:Foreign Language Anxiety(FLA)represents a substantial affective barrier that undermines cognitive performance,motivation,and retention in language learners.Emerging evidence highlights mindfulness-based interventions as promising strategies for enhancing emotional regulation and reducing anxiety across educational contexts.This review synthesizes current research on mindfulness as a psychological intervention,aims to evaluate its efficacy in alleviating FLA,and discusses its broader implications for health-focused educational policy and practice.Methods:Following PRISMA guidelines,we systematically reviewed studies examining the relationships between mindfulness and FLA.Our search of four major databases(November 2023)initially identified 346 articles using terms like“mindfulness AND language anxiety.”After screening,14 studies met our criteria:(1)empirical research in English on mindfulness-FLA relationships;(2)no publication date restrictions.Two independent reviewers selected studies,excluding two due to methodological limitations.We conducted a narrative synthesis given the study heterogeneity(9 correlational and 5 intervention studies).Results:9 non-intervention studies demonstrated that mindfulness is negatively associated with FLA,with 3 studies highlighting the mediating roles of self-efficacy and resilience.5 intervention studies reported inconsistent results regarding the efficacy of mindfulness-based interventions in reducing FLA.Conclusions:The findings suggest that while mindfulness holds promise as a tool to address FLA,its mechanisms and effectiveness require further investigation.This study underscores the need for rigorous research,including Randomized Controlled Trials(RCTs),to inform evidence-based integration of mindfulness into foreign language curricula.For educational policymakers and practitioners,these insights highlight the importance of adopting mindfulness interventions cautiously,ensuring they are tailored to students’needs and supported by evidence.
文摘Anxiety,motivation,and strategy have long been seen as critical in second language acquisition.This study presents a systematic review of the literature on these variables in terms of their relationship with one another,their effects on learning outcomes,and how they are affected by technology-assisted tools in the teaching of Chinese as a second language.This study includes 24 articles for the review study based on the criteria and process of the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocol(PRISMA-P)and the clustering techniques of VOSviewer.It is found that 1)anxiety,motivation,and strategy were interrelated,that is,motivation was negatively associated with anxiety but positively related to strategy,while strategy could positively predict anxiety;2)anxiety could both positively and negatively affect learning outcomes,while motivation and strategy could both positively and insignificantly influence learning outcomes;3)the technology-assisted tools used in the classroom could both positively and negatively affect the levels of these variables and learning outcomes in the L2 Chinese context.The need to explore more complicated relationships between language-specific individual variables themselves and other possible factors that affect these variables,such as cultural ones,are also discussed for future research.
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 National Multidisciplinary Innovation Team of Traditional Chinese Medicine(ZYYCXTD-D-202204)China Postdoctoral Science Foundation(2023M742627)+1 种基金Postdoctoral Fellowship Program of CPSF(GZC20231928)Foundation of State Key Laboratory of Component-based Chinese Medicine(CBCM2023201).
文摘Objective:Generative artificial intelligence(AI)technology,represented by large language models(LLMs),has gradually been developed for traditional Chinese medicine(TCM);however,challenges remain in effectively enhancing AI applications for TCM.Therefore,this study is the first systematic review to analyze LLMs in TCM retrospectively,focusing on and summarizing the evidence of their performance in generative tasks.Methods:We extensively searched electronic databases for articles published until June 2024 to identify publicly available studies on LLMs in TCM.Two investigators independently selected and extracted the related information and evaluation metrics.Based on the available data,this study used descriptive analysis for a comprehensive systematic review of LLM technology related to TCM.Results:Ten studies published between 2023 and 2024 met our eligibility criteria and were included in this review,including 40%LLMs in the TCM vertical domain,40%containing TCM data,and 20%honoring the TCM contribution,with a foundational model parameter range from 1.8 to 33 billion.All included studies used manual or automatic evaluation metrics to evaluate model performance and fully discussed the challenges and contributions through an overview of LLMs in TCM.Conclusions:LLMs have achieved significant advantages in TCM applications and can effectively address intelligent TCM tasks.Further in-depth development of LLMs is needed in various vertical TCM fields,including clinical and fundamental research.Focusing on the functional segmentation development direction of generative AI technologies in TCM application scenarios to meet the practical needs-oriented demands of TCM digitalization is essential.
基金supported by the National Natural Science Foundation of China(No.62306281)the Natural Science Foundation of Zhejiang Province(Nos.LQ23E060006 and LTGG24E050005)the Key Research Plan of Jiaxing City(No.2024BZ20016).
文摘In the era of big data,data-driven technologies are increasingly leveraged by industry to facilitate autonomous learning and intelligent decision-making.However,the challenge of“small samples in big data”emerges when datasets lack the comprehensive information necessary for addressing complex scenarios,which hampers adaptability.Thus,enhancing data completeness is essential.Knowledge-guided virtual sample generation transforms domain knowledge into extensive virtual datasets,thereby reducing dependence on limited real samples and enabling zero-sample fault diagnosis.This study used building air conditioning systems as a case study.We innovatively used the large language model(LLM)to acquire domain knowledge for sample generation,significantly lowering knowledge acquisition costs and establishing a generalized framework for knowledge acquisition in engineering applications.This acquired knowledge guided the design of diffusion boundaries in mega-trend diffusion(MTD),while the Monte Carlo method was used to sample within the diffusion function to create information-rich virtual samples.Additionally,a noise-adding technique was introduced to enhance the information entropy of these samples,thereby improving the robustness of neural networks trained with them.Experimental results showed that training the diagnostic model exclusively with virtual samples achieved an accuracy of 72.80%,significantly surpassing traditional small-sample supervised learning in terms of generalization.This underscores the quality and completeness of the generated virtual samples.
文摘Model evaluation using benchmark datasets is an important method to measure the capability of large language models(LLMs)in specific domains,and it is mainly used to assess the knowledge and reasoning abilities of LLMs.Therefore,in order to better assess the capability of LLMs in the agricultural domain,Agri-Eval was proposed as a benchmark for assessing the knowledge and reasoning ability of LLMs in agriculture.The assessment dataset used in Agri-Eval covered seven major disciplines in the agricultural domain:crop science,horticulture,plant protection,animal husbandry,forest science,aquaculture science,and grass science,and contained a total of 2283 questions.Among domestic general-purpose LLMs,DeepSeek R1 performed best with an accuracy rate of 75.49%.In the realm of international general-purpose LLMs,Gemini 2.0 pro exp 0205 standed out as the top performer,achieving an accuracy rate of 74.28%.As an LLMs in agriculture vertical,Shennong V2.0 outperformed all the LLMs in China,and the answer accuracy rate of agricultural knowledge exceeded that of all the existing general-purpose LLMs.The launch of Agri-Eval helped the LLM developers to comprehensively evaluate the model's capability in the field of agriculture through a variety of tasks and tests to promote the development of the LLMs in the field of agriculture.
基金This study is financed by the European Union-NextGenerationEU,through the National Recovery and Resilience Plan of the Republic of Bulgaria,Project No.BG-RRP-2.013-0001.
文摘Covert timing channels(CTC)exploit network resources to establish hidden communication pathways,posing signi cant risks to data security and policy compliance.erefore,detecting such hidden and dangerous threats remains one of the security challenges. is paper proposes LinguTimeX,a new framework that combines natural language processing with arti cial intelligence,along with explainable Arti cial Intelligence(AI)not only to detect CTC but also to provide insights into the decision process.LinguTimeX performs multidimensional feature extraction by fusing linguistic attributes with temporal network patterns to identify covert channels precisely.LinguTimeX demonstrates strong e ectiveness in detecting CTC across multiple languages;namely English,Arabic,and Chinese.Speci cally,the LSTM and RNN models achieved F1 scores of 90%on the English dataset,89%on the Arabic dataset,and 88%on the Chinese dataset,showcasing their superior performance and ability to generalize across multiple languages. is highlights their robustness in detecting CTCs within security systems,regardless of the language or cultural context of the data.In contrast,the DeepForest model produced F1-scores ranging from 86%to 87%across the same datasets,further con rming its e ectiveness in CTC detection.Although other algorithms also showed reasonable accuracy,the LSTM and RNN models consistently outperformed them in multilingual settings,suggesting that deep learning models might be better suited for this particular problem.
基金the research project LaTe4PoliticES(PID2022-138099OB-I00)funded by MCIN/AEI/10.13039/501100011033 and the European Fund for Regional Development(ERDF)-a way to make Europe.Tomás Bernal-Beltrán is supported by University of Murcia through the predoctoral programme.
文摘The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.
基金funded by the Office of the Vice-President for Research and Development of Cebu Technological University.
文摘This study demonstrates a novel integration of large language models,machine learning,and multicriteria decision-making to investigate self-moderation in small online communities,a topic under-explored compared to user behavior and platform-driven moderation on social media.The proposed methodological framework(1)utilizes large language models for social media post analysis and categorization,(2)employs k-means clustering for content characterization,and(3)incorporates the TODIM(Tomada de Decisão Interativa Multicritério)method to determine moderation strategies based on expert judgments.In general,the fully integrated framework leverages the strengths of these intelligent systems in a more systematic evaluation of large-scale decision problems.When applied in social media moderation,this approach promotes nuanced and context-sensitive self-moderation by taking into account factors such as cultural background and geographic location.The application of this framework is demonstrated within Facebook groups.Eight distinct content clusters encompassing safety,harassment,diversity,and misinformation are identified.Analysis revealed a preference for content removal across all clusters,suggesting a cautious approach towards potentially harmful content.However,the framework also highlights the use of other moderation actions,like account suspension,depending on the content category.These findings contribute to the growing body of research on self-moderation and offer valuable insights for creating safer and more inclusive online spaces within smaller communities.
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.
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant 62276109The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through the Research Group Project number(ORF-2025-585).
文摘The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.
文摘Background:In mental health,recovery is emphasized,and qualitative analyses of service users’narratives have accumulated;however,while qualitative approaches excel at capturing rich context and generating new concepts,they are limited in generalizability and feasible data volume.This study aimed to quantify the subjective life history narratives of users of psychiatric home-visit nursing using natural language processing(NLP)and to clarify the relationships between linguistic features and recovery-related indicators.Methods:We conducted audio-recorded and transcribed semi-structured interviews on daily life verbatim and collected self-report questionnaires(Recovery Assessment Scale[RAS])and clinician ratings(Global Assessment of Functioning[GAF])from Japanese users of psychiatric home-visit nursing.Using the artificial intelligence-based topic-modeling method BERTopic,we extracted topics from the interview texts and calculated each participant’s topic proportions,and then examined associations between topic proportions and recovery-related indicators using Pearson correlation analyses.Results:“School”showed a significant positive correlation with RAS(r=0.39,p=0.05),whereas“Family”showed a significant negative correlation(r=–0.46,p=0.02).GAF was positively correlated with word count(r=0.44,p=0.02)and“Hospital”(r=0.42,p=0.03),and negatively correlated with“Backchannels”(aizuchi)(r=–0.41,p=0.03).Conclusion:The present results suggest that the quantity,quality,and content of narratives can serve as useful indicators of mental health and recovery,and that objective NLP-based analysis of service users’narratives can complement traditional self-report scales and clinician ratings to inform the design of recovery-oriented care in psychiatric home-visit nursing.
文摘War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.
文摘This interview examines the theoretical foundations,pedagogical applications,developmental trajectory,and future directions of the xu-argument.Professor Wang Chuming offers a comprehensive account of the xu-argument,clarifying its theoretical framework,the learning mechanisms underlying xu,and its interface with international theories of second language acquisition(SLA).From the perspective of the xu-argument,he proposes novel interpretations of core issues in SLA.Drawing on the development of the xu-argument,Wang further discusses the essence,directions,and methodology of innovation in SLA theory.He emphasizes that theoretical advances must capture and illuminate underlying natural laws,arguing that innovative approaches are typically rooted in deep reflection on common sense.He also calls for theoretical innovation in SLA in the Chinese context,advocating a robust research paradigm that shifts from local observation to global theoretical generalization,thereby promoting bottom-up theoretical development.In closing,he highlights the promising prospects for SLA theory in the era of artificial intelligence.
基金supported by 2023 Higher Education Scientific Research Planning Project of China Society of Higher Education(No.23PG0408)2023 Philosophy and Social Science Research Programs in Jiangsu Province(No.2023SJSZ0993)+2 种基金Nantong Science and Technology Project(No.JC2023070)Key Project of Jiangsu Province Education Science 14th Five-Year Plan(Grant No.B-b/2024/02/41)the Open Fund of Advanced Cryptography and System Security Key Laboratory of Sichuan Province(Grant No.SKLACSS-202407).
文摘Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.
基金supported by the Fundamental Research Funds for the Central Universities(No.CUC25SG013)the Foundation of Key Laboratory of Education Informatization for Nationalities(Yunnan Normal University),Ministry of Education(No.EIN2024C006).
文摘Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lacks formal task definitions and corresponding benchmarks.To bridge this gap,we define the Automated Online Public Opinion Report Generation(OPOR-Gen)task and construct OPOR-Bench,an event-centric dataset with 463 crisis events across 108 countries(comprising 8.8 K news articles and 185 K tweets).To evaluate report quality,we propose OPOR-Eval,a novel agent-based framework that simulates human expert evaluation.Validation experiments show OPOR-Eval achieves a high Spearman’s correlation(ρ=0.70)with human judgments,though challenges in temporal reasoning persist.This work establishes an initial foundation for advancing automated public opinion reporting research.
基金“A Study on the Value and Path of Integrating Excellent Traditional Chinese Culture Into Intercultural Communication Courses”(ZD2024)a project by the Beijing Higher Education Association,as well as“A Study on the Path of Empowering the Integration of Excellent Traditional Chinese Culture Into Intercultural Communication Courses With Generative AI”(2024),an institutional project of Beijing International Studies University.
文摘This paper undertakes a systematic combing of the development of research on integrating Chinese culture into foreign language education in China from the 1980s to 2025,dividing it into three stages:cultural attachment,cultural compensation,and cultural symbiosis,and reveals the logical shift of the research from the dominance of target language culture to the construction of the subjectivity of Chinese culture.Through quantitative and qualitative analysis of 435 CSSCI papers,three core themes are extracted:what to integrate,why to integrate,and how to integrate.This paper critically analyzes three pairs of contradictions:the imbalance between instrumentality and humanism,the separation of national narrative and individual expression,and the disconnection between traditional inheritance and modern transformation.It is proposed that future research should reconstruct the educational logic based on the Chinese context,integrate the national and individual dimensions,and build a dialogue mechanism between tradition and modernity,so as to provide theoretical and practical reference for the construction of a foreign language education system with Chinese characteristics.
