In the era of AI,especially large models,the importance of open source has become increasingly prominent.First,open source allows innovation to avoid starting from scratch.Through iterative innovation,it promotes tech...In the era of AI,especially large models,the importance of open source has become increasingly prominent.First,open source allows innovation to avoid starting from scratch.Through iterative innovation,it promotes technical exchanges and learning globally.Second,resources required for large model R&D are difficult for a single institution to obtain.The evaluation of general large models also requires the participation of experts from various industries.Third,without open source collaboration,it is difficult to form a unified upper-layer software ecosystem.Therefore,open source has become an important cooperation mechanism to promote the development of AI and large models.There are two cases to illustrate how open source and international standards interact with each other.展开更多
Sarcasm detection in Natural Language Processing(NLP)has become increasingly important,partic-ularly with the rise of social media and non-textual emotional expressions,such as images.Existing methods often rely on se...Sarcasm detection in Natural Language Processing(NLP)has become increasingly important,partic-ularly with the rise of social media and non-textual emotional expressions,such as images.Existing methods often rely on separate image and text modalities,which may not fully utilize the information available from both sources.To address this limitation,we propose a novel multimodal large model,i.e.,the PKME-MLM(Prior Knowledge and Multi-label Emotion analysis based Multimodal Large Model for sarcasm detection).The PKME-MLM aims to enhance sarcasm detection by integrating prior knowledge to extract useful textual information from images,which is then combined with text data for deeper analysis.This method improves the integration of image and text data,addressing the limitation of previous models that process these modalities separately.Additionally,we incorporate multi-label sentiment analysis,refining sentiment labels to improve sarcasm recognition accuracy.This design overcomes the limitations of prior models that treated sentiment classification as a single-label problem,thereby improving sarcasm recognition by distinguishing subtle emotional cues from the text.Experimental results demonstrate that our approach achieves significant performance improvements in multimodal sarcasm detection tasks,with an accuracy(Acc.)of 94.35%,and Macro-Average Precision and Recall reaching 93.92%and 94.21%,respectively.These results highlight the potential of multimodal models in improving sarcasm detection and suggest that further integration of modalities could advance future research.This work also paves the way for incorporating multimodal sentiment analysis into sarcasm detection.展开更多
This study examines the advent of agent interaction(AIx)as a transformative paradigm in humancomputer interaction(HCI),signifying a notable evolution beyond traditional graphical interfaces and touchscreen interaction...This study examines the advent of agent interaction(AIx)as a transformative paradigm in humancomputer interaction(HCI),signifying a notable evolution beyond traditional graphical interfaces and touchscreen interactions.Within the context of large models,AIx is characterized by its innovative interaction patterns and a plethora of application scenarios that hold great potential.The paper highlights the pivotal role of AIx in shaping the future landscape of the large model industry,emphasizing its adoption and necessity from a user's perspective.This study underscores the pivotal role of AIx in dictating the future trajectory of a large model industry by emphasizing the importance of its adoption and necessity from a user-centric perspective.The fundamental drivers of AIx include the introduction of novel capabilities,replication of capabilities(both anthropomorphic and superhuman),migration of capabilities,aggregation of intelligence,and multiplication of capabilities.These elements are essential for propelling innovation,expanding the frontiers of capability,and realizing the exponential superposition of capabilities,thereby mitigating labor redundancy and addressing a spectrum of human needs.Furthermore,this study provides an in-depth analysis of the structural components and operational mechanisms of agents supported by large models.Such advancements significantly enhance the capacity of agents to tackle complex problems and provide intelligent services,thereby facilitating a more intuitive,adaptive,and personalized engagement between humans and machines.The study further delineates four principal categories of interaction patterns that encompass eight distinct modalities of interaction,corresponding to twenty-one specific scenarios,including applications in smart home systems,health assistance,and elderly care.This emphasizes the significance of this new paradigm in advancing HCI,fostering technological advancements,and redefining user experiences.However,it also acknowledges the challenges and ethical considerations that accompany this paradigm shift,recognizing the need for a balanced approach to harness the full potential of AIx in modern society.展开更多
For computer science majors in higher education institutions,programming courses are one of the most important professional foundation courses.Proficiency in independent programming skills is of great help to the stud...For computer science majors in higher education institutions,programming courses are one of the most important professional foundation courses.Proficiency in independent programming skills is of great help to the study of subsequent courses and the personal development of students.In the teaching process of programming courses,online judgement systems are often used to improve students’programming level.Traditional online judgement systems lack guidance for students,and it is often difficult for inexperienced students to find and correct errors in their codes by themselves.We propose an online judgement system that integrates a large model of error correction to help students find errors and improve their programming skills.展开更多
Large models,such as large language models(LLMs),vision-language models(VLMs),and multimodal agents,have become key elements in artificial intelli⁃gence(AI)systems.Their rapid development has greatly improved percepti...Large models,such as large language models(LLMs),vision-language models(VLMs),and multimodal agents,have become key elements in artificial intelli⁃gence(AI)systems.Their rapid development has greatly improved perception,generation,and decision-making in various fields.However,their vast scale and complexity bring about new security challenges.Issues such as backdoor vulnerabilities during training,jailbreaking in multimodal rea⁃soning,and data provenance and copyright auditing have made security a critical focus for both academia and industry.展开更多
This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large mode...This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large models in vertical industries,outlines the challenges and issues confronted in applying large models in the oil and gas sector,and offers prospects for the application of large models in the oil and gas industry.The existing large models can be briefly divided into three categories:large language models,visual large models,and multimodal large models.The application of large models in the oil and gas industry is still in its infancy.Based on open-source large language models,some oil and gas enterprises have released large language model products using methods like fine-tuning and retrieval augmented generation.Scholars have attempted to develop scenario-specific models for oil and gas operations by using visual/multimodal foundation models.A few researchers have constructed pre-trained foundation models for seismic data processing and interpretation,as well as core analysis.The application of large models in the oil and gas industry faces challenges such as current data quantity and quality being difficult to support the training of large models,high research and development costs,and poor algorithm autonomy and control.The application of large models should be guided by the needs of oil and gas business,taking the application of large models as an opportunity to improve data lifecycle management,enhance data governance capabilities,promote the construction of computing power,strengthen the construction of“artificial intelligence+energy”composite teams,and boost the autonomy and control of large model technology.展开更多
The emergence of artificial intelligence natural language large models has brought new dawn for the in-depth empowerment of the industry.Research on key technologies and applications of railway natural language large ...The emergence of artificial intelligence natural language large models has brought new dawn for the in-depth empowerment of the industry.Research on key technologies and applications of railway natural language large model is of great significance to promoting and coordinating the development of railway artificial intelligence.This paper puts forward the application scenarios of railway natural language large model according to the application requirements of railway artificial intelligence;designs the overall architecture of the railway natural language large model by relying on the railway artificial intelligence platform,studies the key technologies of the natural language large model,builds a railway industry large model oriented to intelligent question-answering,and verifies the model with actual data;finally,this paper prospects for the development and application of railway natural language large model from the aspects of railway traffic organization,railway operation safety and passenger service.展开更多
Following the groundbreaking introduction of the Transformer architecture in 2017,the development of Large Language Models(LLMs)formally commenced.In May 2020,Chat GPT-3,with over one hundred billion parameters,entere...Following the groundbreaking introduction of the Transformer architecture in 2017,the development of Large Language Models(LLMs)formally commenced.In May 2020,Chat GPT-3,with over one hundred billion parameters,entered the public eye,marking a significant milestone in LLM advancement.展开更多
To improve the accuracy and generalization of well logging curve reconstruction,this paper proposes an artificial intelligence large language model“Gaia”and conducts model evaluation experiments.By fine-tuning the p...To improve the accuracy and generalization of well logging curve reconstruction,this paper proposes an artificial intelligence large language model“Gaia”and conducts model evaluation experiments.By fine-tuning the pre-trained large language model,the Gaia significantly improved its ability in extracting sequential patterns and spatial features from well-log curves.Leveraging the adapter method for fine-tuning,this model required training only about 1/70 of its original parameters,greatly improving training efficiency.Comparative experiments,ablation experiments,and generalization experiments were designed and conducted using well-log data from 250 wells.In the comparative experiment,the Gaia model was benchmarked against cutting-edge small deep learning models and conventional large language models,demonstrating that the Gaia model reduced the mean absolute error(MAE)by at least 20%.In the ablation experiments,the synergistic effect of the Gaia model's multiple components was validated,with its MAE being at least 30%lower than that of single-component models.In the generalization experiments,the superior performance of the Gaia model in blind-well predictions was further confirmed.Compared to traditional models,the Gaia model is significantly superior in accuracy and generalization for logging curve reconstruction,fully showcasing the potential of large language models in the field of well-logging.This provides a new approach for future intelligent logging data processing.展开更多
The unprecedented scale of large models,such as large language models(LLMs)and text-to-image diffusion models,has raised critical concerns about the unauthorized use of copyrighted data during model training.These con...The unprecedented scale of large models,such as large language models(LLMs)and text-to-image diffusion models,has raised critical concerns about the unauthorized use of copyrighted data during model training.These concerns have spurred a growing demand for dataset copyright auditing techniques,which aim to detect and verify potential infringements in the training data of commercial AI systems.This paper presents a survey of existing auditing solutions,categorizing them across key dimensions:data modality,model training stage,data overlap scenarios,and model access levels.We highlight major trends,including the prevalence of black-box auditing methods and the emphasis on fine-tuning rather than pre-training.Through an in-depth analysis of 12 representative works,we extract four key observations that reveal the limitations of current methods.Furthermore,we identify three open challenges and propose future directions for robust,multimodal,and scalable auditing solutions.Our findings underscore the urgent need to establish standardized benchmarks and develop auditing frameworks that are resilient to low watermark densities and applicable in diverse deployment settings.展开更多
The application of visual-language large models in the field of medical health has gradually become a research focus.The models combine the capability for image understanding and natural language processing,and can si...The application of visual-language large models in the field of medical health has gradually become a research focus.The models combine the capability for image understanding and natural language processing,and can simultaneously process multi-modality data such as medical images and medical reports.These models can not only recognize images,but also understand the semantic relationship between images and texts,effectively realize the integration of medical information,and provide strong support for clinical decision-making and disease diagnosis.The visual-language large model has good performance for specific medical tasks,and also shows strong potential and high intelligence in the general task models.This paper provides a comprehensive review of the visual-language large model in the field of medical health.Specifically,this paper first introduces the basic theoretical basis and technical principles.Then,this paper introduces the specific application scenarios in the field of medical health,including modality fusion,semi-supervised learning,weakly supervised learning,unsupervised learning,cross-domain model and general models.Finally,the challenges including insufficient data,interpretability,and practical deployment are discussed.According to the existing challenges,four potential future development directions are given.展开更多
We proposes an AI-assisted framework for integrated natural disaster prevention and emergency response,leveraging the DeepSeek large language model(LLM)to advance intelligent decision-making in geohazard management.We...We proposes an AI-assisted framework for integrated natural disaster prevention and emergency response,leveraging the DeepSeek large language model(LLM)to advance intelligent decision-making in geohazard management.We systematically analyze the technical pathways for deploying LLMs in disaster scenarios,emphasizing three breakthrough directions:(1)knowledge graph-driven dynamic risk modeling,(2)reinforcement learning-optimized emergency decision systems,and(3)secure local deployment architectures.The DeepSeek model demonstrates unique advantages through its hybrid reasoning mechanism combining semantic analysis with geospatial pattern recognition,enabling cost-effective processing of multi-source data spanning historical disaster records,real-time IoT sensor feeds,and socio-environmental parameters.A modular system architecture is designed to achieve three critical objectives:(a)automated construction of domain-specific knowledge graphs through unsupervised learning of disaster physics relationships,(b)scenario-adaptive resource allocation using risk simulations,and(c)preserving emergency coordination via federated learning across distributed response nodes.The proposed local deployment paradigm addresses critical data security concerns in cross-border disaster management while complying with the FAIR principles(Findable,Accessible,Interoperable,Reusable)for geoscientific data governance.This work establishes a methodological foundation for next-generation AI-earth science convergence in disaster mitigation.展开更多
The rapid advancement of deep learning and the emergence of largescale neural models,such as bidirectional encoder representations from transformers(BERT),generative pre-trained transformer(GPT),and large language mod...The rapid advancement of deep learning and the emergence of largescale neural models,such as bidirectional encoder representations from transformers(BERT),generative pre-trained transformer(GPT),and large language model Meta AI(LLaMa),have brought significant computational and energy challenges.Neuromorphic computing presents a biologically inspired approach to addressing these issues,leveraging event-driven processing and in-memory computation for enhanced energy efficiency.This survey explores the intersection of neuromorphic computing and large-scale deep learning models,focusing on neuromorphic models,learning methods,and hardware.We highlight transferable techniques from deep learning to neuromorphic computing and examine the memoryrelated scalability limitations of current neuromorphic systems.Furthermore,we identify potential directions to enable neuromorphic systems to meet the growing demands of modern AI workloads.展开更多
Deep learning has become a hot field of artificial intelligence,and the deep learning large model framework has become a bridgehead for the active layout of Chinese and foreign technology companies.Large models play a...Deep learning has become a hot field of artificial intelligence,and the deep learning large model framework has become a bridgehead for the active layout of Chinese and foreign technology companies.Large models play a significant role in the application field,greatly improving the efficiency of training and optimization,and contributing to the landing of many innovative artificial intelligence tools.Based on the Chinese PaddlePaddle large model framework,an application system is designed in combination with the intelligent classroom teaching scenario,which uses machine vision algorithms to distinguish and present teachers’and students’behaviors,that is,the digitization and multi-classification scheme of class character states.After having digital data,data analysis can be carried out to evaluate the class status of teachers and students,and the traditional subjective judgment such as peacetime grades and teaching ability can be upgraded to the objective judgment of artificial intelligence.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
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
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
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
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
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
文摘In the era of AI,especially large models,the importance of open source has become increasingly prominent.First,open source allows innovation to avoid starting from scratch.Through iterative innovation,it promotes technical exchanges and learning globally.Second,resources required for large model R&D are difficult for a single institution to obtain.The evaluation of general large models also requires the participation of experts from various industries.Third,without open source collaboration,it is difficult to form a unified upper-layer software ecosystem.Therefore,open source has become an important cooperation mechanism to promote the development of AI and large models.There are two cases to illustrate how open source and international standards interact with each other.
基金funding partly by the National Natural Science Foundation of China under grant number 61701179.
文摘Sarcasm detection in Natural Language Processing(NLP)has become increasingly important,partic-ularly with the rise of social media and non-textual emotional expressions,such as images.Existing methods often rely on separate image and text modalities,which may not fully utilize the information available from both sources.To address this limitation,we propose a novel multimodal large model,i.e.,the PKME-MLM(Prior Knowledge and Multi-label Emotion analysis based Multimodal Large Model for sarcasm detection).The PKME-MLM aims to enhance sarcasm detection by integrating prior knowledge to extract useful textual information from images,which is then combined with text data for deeper analysis.This method improves the integration of image and text data,addressing the limitation of previous models that process these modalities separately.Additionally,we incorporate multi-label sentiment analysis,refining sentiment labels to improve sarcasm recognition accuracy.This design overcomes the limitations of prior models that treated sentiment classification as a single-label problem,thereby improving sarcasm recognition by distinguishing subtle emotional cues from the text.Experimental results demonstrate that our approach achieves significant performance improvements in multimodal sarcasm detection tasks,with an accuracy(Acc.)of 94.35%,and Macro-Average Precision and Recall reaching 93.92%and 94.21%,respectively.These results highlight the potential of multimodal models in improving sarcasm detection and suggest that further integration of modalities could advance future research.This work also paves the way for incorporating multimodal sentiment analysis into sarcasm detection.
文摘This study examines the advent of agent interaction(AIx)as a transformative paradigm in humancomputer interaction(HCI),signifying a notable evolution beyond traditional graphical interfaces and touchscreen interactions.Within the context of large models,AIx is characterized by its innovative interaction patterns and a plethora of application scenarios that hold great potential.The paper highlights the pivotal role of AIx in shaping the future landscape of the large model industry,emphasizing its adoption and necessity from a user's perspective.This study underscores the pivotal role of AIx in dictating the future trajectory of a large model industry by emphasizing the importance of its adoption and necessity from a user-centric perspective.The fundamental drivers of AIx include the introduction of novel capabilities,replication of capabilities(both anthropomorphic and superhuman),migration of capabilities,aggregation of intelligence,and multiplication of capabilities.These elements are essential for propelling innovation,expanding the frontiers of capability,and realizing the exponential superposition of capabilities,thereby mitigating labor redundancy and addressing a spectrum of human needs.Furthermore,this study provides an in-depth analysis of the structural components and operational mechanisms of agents supported by large models.Such advancements significantly enhance the capacity of agents to tackle complex problems and provide intelligent services,thereby facilitating a more intuitive,adaptive,and personalized engagement between humans and machines.The study further delineates four principal categories of interaction patterns that encompass eight distinct modalities of interaction,corresponding to twenty-one specific scenarios,including applications in smart home systems,health assistance,and elderly care.This emphasizes the significance of this new paradigm in advancing HCI,fostering technological advancements,and redefining user experiences.However,it also acknowledges the challenges and ethical considerations that accompany this paradigm shift,recognizing the need for a balanced approach to harness the full potential of AIx in modern society.
基金supported by Research and Construction of Experimental Teaching Aid Platform for Programming under the Teaching Reform Research Project of Shandong University。
文摘For computer science majors in higher education institutions,programming courses are one of the most important professional foundation courses.Proficiency in independent programming skills is of great help to the study of subsequent courses and the personal development of students.In the teaching process of programming courses,online judgement systems are often used to improve students’programming level.Traditional online judgement systems lack guidance for students,and it is often difficult for inexperienced students to find and correct errors in their codes by themselves.We propose an online judgement system that integrates a large model of error correction to help students find errors and improve their programming skills.
文摘Large models,such as large language models(LLMs),vision-language models(VLMs),and multimodal agents,have become key elements in artificial intelli⁃gence(AI)systems.Their rapid development has greatly improved perception,generation,and decision-making in various fields.However,their vast scale and complexity bring about new security challenges.Issues such as backdoor vulnerabilities during training,jailbreaking in multimodal rea⁃soning,and data provenance and copyright auditing have made security a critical focus for both academia and industry.
基金Supported by the National Natural Science Foundation of China(72088101,42372175)PetroChina Science and Technology Innovation Fund Program(2021DQ02-0904)。
文摘This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large models in vertical industries,outlines the challenges and issues confronted in applying large models in the oil and gas sector,and offers prospects for the application of large models in the oil and gas industry.The existing large models can be briefly divided into three categories:large language models,visual large models,and multimodal large models.The application of large models in the oil and gas industry is still in its infancy.Based on open-source large language models,some oil and gas enterprises have released large language model products using methods like fine-tuning and retrieval augmented generation.Scholars have attempted to develop scenario-specific models for oil and gas operations by using visual/multimodal foundation models.A few researchers have constructed pre-trained foundation models for seismic data processing and interpretation,as well as core analysis.The application of large models in the oil and gas industry faces challenges such as current data quantity and quality being difficult to support the training of large models,high research and development costs,and poor algorithm autonomy and control.The application of large models should be guided by the needs of oil and gas business,taking the application of large models as an opportunity to improve data lifecycle management,enhance data governance capabilities,promote the construction of computing power,strengthen the construction of“artificial intelligence+energy”composite teams,and boost the autonomy and control of large model technology.
文摘The emergence of artificial intelligence natural language large models has brought new dawn for the in-depth empowerment of the industry.Research on key technologies and applications of railway natural language large model is of great significance to promoting and coordinating the development of railway artificial intelligence.This paper puts forward the application scenarios of railway natural language large model according to the application requirements of railway artificial intelligence;designs the overall architecture of the railway natural language large model by relying on the railway artificial intelligence platform,studies the key technologies of the natural language large model,builds a railway industry large model oriented to intelligent question-answering,and verifies the model with actual data;finally,this paper prospects for the development and application of railway natural language large model from the aspects of railway traffic organization,railway operation safety and passenger service.
文摘Following the groundbreaking introduction of the Transformer architecture in 2017,the development of Large Language Models(LLMs)formally commenced.In May 2020,Chat GPT-3,with over one hundred billion parameters,entered the public eye,marking a significant milestone in LLM advancement.
基金Supported by the National Natural Science Foundation of China(52288101)National Key R&D Program of China(2024YFF1500600)。
文摘To improve the accuracy and generalization of well logging curve reconstruction,this paper proposes an artificial intelligence large language model“Gaia”and conducts model evaluation experiments.By fine-tuning the pre-trained large language model,the Gaia significantly improved its ability in extracting sequential patterns and spatial features from well-log curves.Leveraging the adapter method for fine-tuning,this model required training only about 1/70 of its original parameters,greatly improving training efficiency.Comparative experiments,ablation experiments,and generalization experiments were designed and conducted using well-log data from 250 wells.In the comparative experiment,the Gaia model was benchmarked against cutting-edge small deep learning models and conventional large language models,demonstrating that the Gaia model reduced the mean absolute error(MAE)by at least 20%.In the ablation experiments,the synergistic effect of the Gaia model's multiple components was validated,with its MAE being at least 30%lower than that of single-component models.In the generalization experiments,the superior performance of the Gaia model in blind-well predictions was further confirmed.Compared to traditional models,the Gaia model is significantly superior in accuracy and generalization for logging curve reconstruction,fully showcasing the potential of large language models in the field of well-logging.This provides a new approach for future intelligent logging data processing.
基金supported in part by NSFC under Grant Nos.62402379,U22A2029 and U24A20237.
文摘The unprecedented scale of large models,such as large language models(LLMs)and text-to-image diffusion models,has raised critical concerns about the unauthorized use of copyrighted data during model training.These concerns have spurred a growing demand for dataset copyright auditing techniques,which aim to detect and verify potential infringements in the training data of commercial AI systems.This paper presents a survey of existing auditing solutions,categorizing them across key dimensions:data modality,model training stage,data overlap scenarios,and model access levels.We highlight major trends,including the prevalence of black-box auditing methods and the emphasis on fine-tuning rather than pre-training.Through an in-depth analysis of 12 representative works,we extract four key observations that reveal the limitations of current methods.Furthermore,we identify three open challenges and propose future directions for robust,multimodal,and scalable auditing solutions.Our findings underscore the urgent need to establish standardized benchmarks and develop auditing frameworks that are resilient to low watermark densities and applicable in diverse deployment settings.
基金The Natural Science Foundation of Hebei Province(F2024501044).
文摘The application of visual-language large models in the field of medical health has gradually become a research focus.The models combine the capability for image understanding and natural language processing,and can simultaneously process multi-modality data such as medical images and medical reports.These models can not only recognize images,but also understand the semantic relationship between images and texts,effectively realize the integration of medical information,and provide strong support for clinical decision-making and disease diagnosis.The visual-language large model has good performance for specific medical tasks,and also shows strong potential and high intelligence in the general task models.This paper provides a comprehensive review of the visual-language large model in the field of medical health.Specifically,this paper first introduces the basic theoretical basis and technical principles.Then,this paper introduces the specific application scenarios in the field of medical health,including modality fusion,semi-supervised learning,weakly supervised learning,unsupervised learning,cross-domain model and general models.Finally,the challenges including insufficient data,interpretability,and practical deployment are discussed.According to the existing challenges,four potential future development directions are given.
基金funded by the Chongqing Water Resources Bureau,China(Project No.CQS24C00836).
文摘We proposes an AI-assisted framework for integrated natural disaster prevention and emergency response,leveraging the DeepSeek large language model(LLM)to advance intelligent decision-making in geohazard management.We systematically analyze the technical pathways for deploying LLMs in disaster scenarios,emphasizing three breakthrough directions:(1)knowledge graph-driven dynamic risk modeling,(2)reinforcement learning-optimized emergency decision systems,and(3)secure local deployment architectures.The DeepSeek model demonstrates unique advantages through its hybrid reasoning mechanism combining semantic analysis with geospatial pattern recognition,enabling cost-effective processing of multi-source data spanning historical disaster records,real-time IoT sensor feeds,and socio-environmental parameters.A modular system architecture is designed to achieve three critical objectives:(a)automated construction of domain-specific knowledge graphs through unsupervised learning of disaster physics relationships,(b)scenario-adaptive resource allocation using risk simulations,and(c)preserving emergency coordination via federated learning across distributed response nodes.The proposed local deployment paradigm addresses critical data security concerns in cross-border disaster management while complying with the FAIR principles(Findable,Accessible,Interoperable,Reusable)for geoscientific data governance.This work establishes a methodological foundation for next-generation AI-earth science convergence in disaster mitigation.
文摘The rapid advancement of deep learning and the emergence of largescale neural models,such as bidirectional encoder representations from transformers(BERT),generative pre-trained transformer(GPT),and large language model Meta AI(LLaMa),have brought significant computational and energy challenges.Neuromorphic computing presents a biologically inspired approach to addressing these issues,leveraging event-driven processing and in-memory computation for enhanced energy efficiency.This survey explores the intersection of neuromorphic computing and large-scale deep learning models,focusing on neuromorphic models,learning methods,and hardware.We highlight transferable techniques from deep learning to neuromorphic computing and examine the memoryrelated scalability limitations of current neuromorphic systems.Furthermore,we identify potential directions to enable neuromorphic systems to meet the growing demands of modern AI workloads.
基金Education Department of Hainan Provincial(Hnky2024-43)Sanya University’s Industry-Education Integration Project(USY-CJRH2313)Financial Innovation and Multi-Asset Intelligent Trading Laboratory of the Key Laboratory of Philosophy and Social Sciences in Hainan Province of University of Sanya.
文摘Deep learning has become a hot field of artificial intelligence,and the deep learning large model framework has become a bridgehead for the active layout of Chinese and foreign technology companies.Large models play a significant role in the application field,greatly improving the efficiency of training and optimization,and contributing to the landing of many innovative artificial intelligence tools.Based on the Chinese PaddlePaddle large model framework,an application system is designed in combination with the intelligent classroom teaching scenario,which uses machine vision algorithms to distinguish and present teachers’and students’behaviors,that is,the digitization and multi-classification scheme of class character states.After having digital data,data analysis can be carried out to evaluate the class status of teachers and students,and the traditional subjective judgment such as peacetime grades and teaching ability can be upgraded to the objective judgment of artificial intelligence.
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.
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 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.
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.
