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
This review presents a comprehensive and forward-looking analysis of how Large Language Models(LLMs)are transforming knowledge discovery in the rational design of advancedmicro/nano electrocatalyst materials.Electroca...This review presents a comprehensive and forward-looking analysis of how Large Language Models(LLMs)are transforming knowledge discovery in the rational design of advancedmicro/nano electrocatalyst materials.Electrocatalysis is central to sustainable energy and environmental technologies,but traditional catalyst discovery is often hindered by high complexity,fragmented knowledge,and inefficiencies.LLMs,particularly those based on Transformer architectures,offer unprecedented capabilities in extracting,synthesizing,and generating scientific knowledge from vast unstructured textual corpora.This work provides the first structured synthesis of how LLMs have been leveraged across various electrocatalysis tasks,including automated information extraction from literature,text-based property prediction,hypothesis generation,synthesis planning,and knowledge graph construction.We comparatively analyze leading LLMs and domain-specific frameworks(e.g.,CatBERTa,CataLM,CatGPT)in terms of methodology,application scope,performance metrics,and limitations.Through curated case studies across key electrocatalytic reactions—HER,OER,ORR,and CO_(2)RR—we highlight emerging trends such as the growing use of embedding-based prediction,retrieval-augmented generation,and fine-tuned scientific LLMs.The review also identifies persistent challenges,including data heterogeneity,hallucination risks,lack of standard benchmarks,and limited multimodal integration.Importantly,we articulate future research directions,such as the development of multimodal and physics-informedMatSci-LLMs,enhanced interpretability tools,and the integration of LLMswith selfdriving laboratories for autonomous discovery.By consolidating fragmented advances and outlining a unified research roadmap,this review provides valuable guidance for both materials scientists and AI practitioners seeking to accelerate catalyst innovation through large language model technologies.展开更多
Large language models(LLMs)have undergone significant expansion and have been increasingly integrated across various domains.Notably,in the realm of robot task planning,LLMs harness their advanced reasoning and langua...Large language models(LLMs)have undergone significant expansion and have been increasingly integrated across various domains.Notably,in the realm of robot task planning,LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions.However,for embodied tasks,where robots interact with complex environments,textonly LLMs often face challenges due to a lack of compatibility with robotic visual perception.This study provides a comprehensive overview of the emerging integration of LLMs and multimodal LLMs into various robotic tasks.Additionally,we propose a framework that utilizes multimodal GPT-4V to enhance embodied task planning through the combination of natural language instructions and robot visual perceptions.Our results,based on diverse datasets,indicate that GPT-4V effectively enhances robot performance in embodied tasks.This extensive survey and evaluation of LLMs and multimodal LLMs across a variety of robotic tasks enriches the understanding of LLM-centric embodied intelligence and provides forward-looking insights towards bridging the gap in Human-Robot-Environment interaction.展开更多
Purpose:Evaluating the quality of academic journal articles is a time consuming but critical task for national research evaluation exercises,appointments and promotion.It is therefore important to investigate whether ...Purpose:Evaluating the quality of academic journal articles is a time consuming but critical task for national research evaluation exercises,appointments and promotion.It is therefore important to investigate whether Large Language Models(LLMs)can play a role in this process.Design/methodology/approach:This article assesses which ChatGPT inputs(full text without tables,figures,and references;title and abstract;title only)produce better quality score estimates,and the extent to which scores are affected by ChatGPT models and system prompts.Findings:The optimal input is the article title and abstract,with average ChatGPT scores based on these(30 iterations on a dataset of 51 papers)correlating at 0.67 with human scores,the highest ever reported.ChatGPT 4o is slightly better than 3.5-turbo(0.66),and 4o-mini(0.66).Research limitations:The data is a convenience sample of the work of a single author,it only includes one field,and the scores are self-evaluations.Practical implications:The results suggest that article full texts might confuse LLM research quality evaluations,even though complex system instructions for the task are more effective than simple ones.Thus,whilst abstracts contain insufficient information for a thorough assessment of rigour,they may contain strong pointers about originality and significance.Finally,linear regression can be used to convert the model scores into the human scale scores,which is 31%more accurate than guessing.Originality/value:This is the first systematic comparison of the impact of different prompts,parameters and inputs for ChatGPT research quality evaluations.展开更多
The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation capabilities.De...The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation capabilities.Despite their transformative impact in fields such as machine translation and intelligent dialogue systems,LLMs face significant challenges.These challenges include safety,security,and privacy concerns that undermine their trustworthiness and effectiveness,such as hallucinations,backdoor attacks,and privacy leakage.Previous works often conflated safety issues with security concerns.In contrast,our study provides clearer and more reasonable definitions for safety,security,and privacy within the context of LLMs.Building on these definitions,we provide a comprehensive overview of the vulnerabilities and defense mechanisms related to safety,security,and privacy in LLMs.Additionally,we explore the unique research challenges posed by LLMs and suggest potential avenues for future research,aiming to enhance the robustness and reliability of LLMs in the face of emerging threats.展开更多
Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, ...Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently,researchers have explored the potential of using large language models(LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.展开更多
ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential sec...ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential security risks that need to be carefully evaluated and addressed. In this survey, we provide an overview of the current state of research on security of using ChatGPT, with aspects of bias, disinformation, ethics, misuse,attacks and privacy. We review and discuss the literature on these topics and highlight open research questions and future directions.Through this survey, we aim to contribute to the academic discourse on AI security, enriching the understanding of potential risks and mitigations. We anticipate that this survey will be valuable for various stakeholders involved in AI development and usage, including AI researchers, developers, policy makers, and end-users.展开更多
Large size titanium alloy parts are widely used in aerospace.However,they are difficult to manufacture using mechanical cutting technology because of severe tool wear.Electrochemical jet machining is a promising techn...Large size titanium alloy parts are widely used in aerospace.However,they are difficult to manufacture using mechanical cutting technology because of severe tool wear.Electrochemical jet machining is a promising technology to achieve high efficiency,because it has high machining flexibility and no machining tool wear.However,reports on the macro electrochemical jet machining of large size titanium alloy parts are very scarce,because it is difficult to achieve effective constraint of the flow field in macro electrochemical jet machining.In addition,titanium alloy is very sensitive to fluctuation of the flow field,and a turbulent flow field would lead to serious stray corrosion.This paper reports a series of investigations of the electrochemical jet machining of titanium alloy parts.Based on the flow analysis and experiments,the machining flow field was effectively constrained.TB6 titanium alloy part with a perimeter of one meter was machined.The machined surface was smooth with no obvious machining defects.The machining process was particularly stable with no obvious spark discharge.The research provides a reference for the application of electrochemical jet machining technology to achieve large allowance material removal in the machining of large titanium alloy parts.展开更多
BACKGROUND Inflammatory bowel disease(IBD)is a global health burden that affects millions of individuals worldwide,necessitating extensive patient education.Large language models(LLMs)hold promise for addressing patie...BACKGROUND Inflammatory bowel disease(IBD)is a global health burden that affects millions of individuals worldwide,necessitating extensive patient education.Large language models(LLMs)hold promise for addressing patient information needs.However,LLM use to deliver accurate and comprehensible IBD-related medical information has yet to be thoroughly investigated.AIM To assess the utility of three LLMs(ChatGPT-4.0,Claude-3-Opus,and Gemini-1.5-Pro)as a reference point for patients with IBD.METHODS In this comparative study,two gastroenterology experts generated 15 IBD-related questions that reflected common patient concerns.These questions were used to evaluate the performance of the three LLMs.The answers provided by each model were independently assessed by three IBD-related medical experts using a Likert scale focusing on accuracy,comprehensibility,and correlation.Simultaneously,three patients were invited to evaluate the comprehensibility of their answers.Finally,a readability assessment was performed.RESULTS Overall,each of the LLMs achieved satisfactory levels of accuracy,comprehensibility,and completeness when answering IBD-related questions,although their performance varies.All of the investigated models demonstrated strengths in providing basic disease information such as IBD definition as well as its common symptoms and diagnostic methods.Nevertheless,when dealing with more complex medical advice,such as medication side effects,dietary adjustments,and complication risks,the quality of answers was inconsistent between the LLMs.Notably,Claude-3-Opus generated answers with better readability than the other two models.CONCLUSION LLMs have the potential as educational tools for patients with IBD;however,there are discrepancies between the models.Further optimization and the development of specialized models are necessary to ensure the accuracy and safety of the information provided.展开更多
The design of casting gating system directly determines the solidification sequence,defect severity,and overall quality of the casting.A novel machine learning strategy was developed to design the counter pressure cas...The design of casting gating system directly determines the solidification sequence,defect severity,and overall quality of the casting.A novel machine learning strategy was developed to design the counter pressure casting gating system of a large thin-walled cabin casting.A high-quality dataset was established through orthogonal experiments combined with design criteria for the gating system.Spearman’s correlation analysis was used to select high-quality features.The gating system dimensions were predicted using a gated recurrent unit(GRU)recurrent neural network and an elastic network model.Using EasyCast and ProCAST casting software,a comparative analysis of the flow field,temperature field,and solidification field can be conducted to demonstrate the achievement of steady filling and top-down sequential solidification.Compared to the empirical formula method,this method eliminates trial-and-error iterations,reduces porosity,reduces casting defect volume from 11.23 cubic centimeters to 2.23 cubic centimeters,eliminates internal casting defects through the incorporation of an internally cooled iron,fulfilling the goal of intelligent gating system design.展开更多
In recent years,Volunteered Geographic Information(VGI)has emerged as a crucial source of mapping data,contributed by users through crowdsourcing platforms such as OpenStreetMap.This paper presents a novel approach th...In recent years,Volunteered Geographic Information(VGI)has emerged as a crucial source of mapping data,contributed by users through crowdsourcing platforms such as OpenStreetMap.This paper presents a novel approach that Integrates Large Language Models(LLMs)into a fully automated mapping workflow,utilizing VGI data.The process leverages Prompt Engineering,which involves designing and optimizing input instructions to ensure the LLM produces desired mapping outputs.By constructing precise and detailed prompts,LLM agents are able to accurately interpret mapping requirements,and autonomously extract,analyze,and process VGI geospatial data.They dynamically interact with mapping tools to automate the entire mapping process—from data acquisition to map generation.This approach significantly streamlines the creation of high-quality mapping outputs,reducing the time and resources typically required for such tasks.Moreover,the system lowers the barrier for non-expert users,enabling them to generate accurate maps without extensive technical expertise.Through various case studies,we demonstrate the LLM application across different mapping scenarios,highlighting its potential to enhance the efficiency,accuracy,and accessibility of map production.The results suggest that LLM-powered mapping systems can not only optimize VGI data processing but also expand the usability of ubiquitous mapping across diverse fields,including urban planning and infrastructure development.展开更多
Background:The prognostic significance of the chemokine receptor CCR7 in diffuse large B-cell lymphoma(DLBCL)has been reported previously.However,the detailed mechanisms of CCR7 in DLBCL,particularly regarding its int...Background:The prognostic significance of the chemokine receptor CCR7 in diffuse large B-cell lymphoma(DLBCL)has been reported previously.However,the detailed mechanisms of CCR7 in DLBCL,particularly regarding its interaction with lenalidomide treatment,are not fully understood.Methods:Our study utilized bioinformatics approaches to identify hub genes in SU-DHL-2 cell lines treated with lenalidomide compared to control groups.Immunohistochemical data and clinical information from 122 patients with DLBCL were analyzed to assess the correlation of CCR7 and p-ERK1/2 expression with the prognosis of DLBCL.Furthermore,in vitro and in vivo experiments were conducted to clarify the role of CCR7 in the response of DLBCL to lenalidomide treatment.Results:Our bioinformatics analysis pinpointed CCR7 as a hub gene in the context of lenalidomide treatment in DLBCL.Notably,31.14%and 36.0%(44/122)of DLBCL cases showed positive expression for CCR7 and ERK1/2 respectively,establishing them as independent prognostic factors for adverse outcomes in DLBCL via multivariate Cox regression analysis.Additionally,our studies demonstrated that the external application of the protein CCL21 promoted proliferation,migration,invasion,and activation of the ERK1/2 pathway in SU-DHL-2 and OCI-LY3 cell lines with high levels of CCR7 expression.This effect was mitigated by CCR7 silencing through siRNA,application of ERK inhibitors,or lenalidomide treatment.In vivo experiments reinforced the efficacy of lenalidomide,significantly reducing tumor growth rate,tumor mass,serum total LDH levels,and expression of CCR7 and p-ERK1/2 in a SUDHL-2 xenograft model in nude mice(p<0.05).Conclusion:Our study clarifies the potential role of the CCL21/CCR7/ERK1/2 axis in the therapeutic effects of lenalidomide in DLBCL treatment.展开更多
Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have e...Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.展开更多
The rapid advancement of Artificial Intelligence(AI)and Large Language Models(LLMs)has led to their increasing integration into various domains,from text generation and translation to question-answering.However,a crit...The rapid advancement of Artificial Intelligence(AI)and Large Language Models(LLMs)has led to their increasing integration into various domains,from text generation and translation to question-answering.However,a critical question remains:do these sophisticated models,much like humans,exhibit susceptibility to cognitive biases?Understanding the presence and nature of such biases in AI is paramount for assessing their reliability,enhancing their performance,and predicting their societal impact.This research specifically investigates the susceptibility of Google’s Gemini 1.5 Pro and DeepSeek,two prominent LLMs,to framing effects and confirmation bias.The study meticulously designed a series of experimental trials,systematically manipulating information proportions and presentation orders to evaluate these biases.In the framing effect experiment,a genetic testing decision-making scenario was constructed.The proportion of positive and negative information(e.g.,20%,50%,or 80%positive)and their presentation order were varied.The models’inclination towards undergoing genetic testing was recorded.For the confirmation bias experiment,two reports-one positive and one negative-about“RoboTaxi”autonomous vehicles were provided.The proportion of erroneous information within these reports(10%,30%,and 50%)and their presentation order were systematically altered,and the models’support for each report was assessed.The findings demonstrate that both Gemini 1.5 Pro and DeepSeek are susceptible to framing effects.In the genetic testing scenario,their decision-making was primarily influenced by the proportion of positive and negative information presented.When the proportion of positive information was higher,both models showed a greater inclination to recommend or proceed with genetic testing.Conversely,a higher proportion of negative information led to greater caution or a tendency not to recommend the testing.Importantly,the order in which this information was presented did not significantly influence their decisions in the framing effect scenarios.Regarding confirmation bias,the two models exhibited distinct behaviors.Gemini 1.5 Pro did not show an overall preference for either positive or negative reports.However,its judgments were significantly influenced by the order of information presentation,demonstrating a“recency effect,”meaning it tended to support the report presented later.The proportion of erroneous information within the reports had no significant impact on Gemini 1.5 Pro’s decisions.In contrast,DeepSeek exhibited an overall confirmation bias,showing a clear preference for positive reports.Similar to Gemini 1.5 Pro,DeepSeek’s decisions were also significantly affected by the order of information presentation,while the proportion of misinformation had no significant effect.These results reveal human-like cognitive vulnerabilities in advanced LLMs,highlighting critical challenges to their reliability and objectivity in decision-making processes.Gemini 1.5 Pro’s sensitivity to presentation order and DeepSeek’s general preference for positive information,coupled with its sensitivity to order,underscore the need for careful evaluation of potential cognitive biases during the development and application of AI.The study suggests that effective measures are necessary to mitigate these biases and prevent potential negative societal impacts.Future research should include a broader range of models for comparative analysis and explore more complex interactive scenarios to further understand and address these phenomena.The findings contribute significantly to understanding the limitations and capabilities of current AI systems,guiding their responsible development,and anticipating their potential societal implications.展开更多
We study the two-dimensional(2D)Cauchy problem of nonhomogeneous Boussinesq system for magnetohydrodynamics convection without heat diffusion in the whole plane.Based on delicate weighted estimates,we derive the globa...We study the two-dimensional(2D)Cauchy problem of nonhomogeneous Boussinesq system for magnetohydrodynamics convection without heat diffusion in the whole plane.Based on delicate weighted estimates,we derive the global existence and uniqueness of strong solutions.In particular,the initial data can be arbitrarily large and the initial density may contain vacuum states and even have compact support.展开更多
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
Smart contracts on the Ethereum blockchain continue to revolutionize decentralized applications (dApps) by allowing for self-executing agreements. However, bad actors have continuously found ways to exploit smart cont...Smart contracts on the Ethereum blockchain continue to revolutionize decentralized applications (dApps) by allowing for self-executing agreements. However, bad actors have continuously found ways to exploit smart contracts for personal financial gain, which undermines the integrity of the Ethereum blockchain. This paper proposes a computer program called SADA (Static and Dynamic Analyzer), a novel approach to smart contract vulnerability detection using multiple Large Language Model (LLM) agents to analyze and flag suspicious Solidity code for Ethereum smart contracts. SADA not only improves upon existing vulnerability detection methods but also paves the way for more secure smart contract development practices in the rapidly evolving blockchain ecosystem.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
Stall flutter poses great challenges to flight safety.To alleviate this problem,a steady blowing control considering the perturbation and wake-induced vibration at a large angle of attack is developed in this paper,wh...Stall flutter poses great challenges to flight safety.To alleviate this problem,a steady blowing control considering the perturbation and wake-induced vibration at a large angle of attack is developed in this paper,where two blowings are configured on upper and lower tail surfaces to suppress the stall flutter.The stall flutter with one-degree-of-freedom is first evaluated by numerical simulation.The equation of motion for stall flutter is solved by the Newmark-β method.Then,the stall flutter responses for five blowing speeds,i.e.,0,4,12,20,and 28 m/s under the airspeed range of 3–9 m/s,are studied in detail.The stall flutter suppression mechanism can be summarized as follows:a large blowing speed can inject energy into the boundary layer and enhance the high-pressure zone,which delays the flow separation on the suction surface.In this way,the formation of the leading-edge separation vortex is suppressed.Thus,the dynamic stall vortex is weakened and accelerates shedding.In addition,the driving moment is reduced,which leads to a decrement in the stall flutter amplitude.When the blowing speed is 28 m/s(stall flutter amplitude=0.1357 rad),compared with uncontrolled case(stall flutter amplitude=0.6002 rad),the amplitude can decrease by 77.39%,which demonstrates the effectiveness of the proposed steady blowing based active control strategy.展开更多
A two-dimensional large eddy simulation numerical model is proposed to study the transient vortex flow and pressure oscillation of a large-aspect-ratio solid rocket motor.The numerical model is validated through exper...A two-dimensional large eddy simulation numerical model is proposed to study the transient vortex flow and pressure oscillation of a large-aspect-ratio solid rocket motor.The numerical model is validated through experimental data,finite element analysis and cumulative error analysis.The numerical simulations are executed to obtain the characteristics of the vortex-acoustic and pressure oscillation.The results show that the burning surface regression decreases the motor aspect ratio,increasing the corresponding natural frequency from 260 Hz to 293 Hz.The pressure oscillation phenomenon is formed due to the vortex-acoustic coupling.Decreasing the corner vortex shedding intensity shows negative effects on the dimensionless amplitude of the pressure oscillation.The head cavity without the injection can decrease the vortex-acoustic coupling level at the acoustic pressure antinode.The modified motor with head cavity can obtain a lower dimensionless oscillating pressure amplitude 0.00149 in comparison with 0.00895 of the original motor.The aspect ratio and volume of the head cavity without the injection have great effects on the pressure oscillation suppression,particularly at the low aspect ratio or large volume.The reason is that the mass in the region around the acoustic pressure antinode is extracted centrally,reducing the energy contribution to the acoustic system.With the volume increasing,the acoustic energy capacity increases.展开更多
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.
文摘This review presents a comprehensive and forward-looking analysis of how Large Language Models(LLMs)are transforming knowledge discovery in the rational design of advancedmicro/nano electrocatalyst materials.Electrocatalysis is central to sustainable energy and environmental technologies,but traditional catalyst discovery is often hindered by high complexity,fragmented knowledge,and inefficiencies.LLMs,particularly those based on Transformer architectures,offer unprecedented capabilities in extracting,synthesizing,and generating scientific knowledge from vast unstructured textual corpora.This work provides the first structured synthesis of how LLMs have been leveraged across various electrocatalysis tasks,including automated information extraction from literature,text-based property prediction,hypothesis generation,synthesis planning,and knowledge graph construction.We comparatively analyze leading LLMs and domain-specific frameworks(e.g.,CatBERTa,CataLM,CatGPT)in terms of methodology,application scope,performance metrics,and limitations.Through curated case studies across key electrocatalytic reactions—HER,OER,ORR,and CO_(2)RR—we highlight emerging trends such as the growing use of embedding-based prediction,retrieval-augmented generation,and fine-tuned scientific LLMs.The review also identifies persistent challenges,including data heterogeneity,hallucination risks,lack of standard benchmarks,and limited multimodal integration.Importantly,we articulate future research directions,such as the development of multimodal and physics-informedMatSci-LLMs,enhanced interpretability tools,and the integration of LLMswith selfdriving laboratories for autonomous discovery.By consolidating fragmented advances and outlining a unified research roadmap,this review provides valuable guidance for both materials scientists and AI practitioners seeking to accelerate catalyst innovation through large language model technologies.
基金supported by National Natural Science Foundation of China(62376219 and 62006194)Foundational Research Project in Specialized Discipline(Grant No.G2024WD0146)Faculty Construction Project(Grant No.24GH0201148).
文摘Large language models(LLMs)have undergone significant expansion and have been increasingly integrated across various domains.Notably,in the realm of robot task planning,LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions.However,for embodied tasks,where robots interact with complex environments,textonly LLMs often face challenges due to a lack of compatibility with robotic visual perception.This study provides a comprehensive overview of the emerging integration of LLMs and multimodal LLMs into various robotic tasks.Additionally,we propose a framework that utilizes multimodal GPT-4V to enhance embodied task planning through the combination of natural language instructions and robot visual perceptions.Our results,based on diverse datasets,indicate that GPT-4V effectively enhances robot performance in embodied tasks.This extensive survey and evaluation of LLMs and multimodal LLMs across a variety of robotic tasks enriches the understanding of LLM-centric embodied intelligence and provides forward-looking insights towards bridging the gap in Human-Robot-Environment interaction.
文摘Purpose:Evaluating the quality of academic journal articles is a time consuming but critical task for national research evaluation exercises,appointments and promotion.It is therefore important to investigate whether Large Language Models(LLMs)can play a role in this process.Design/methodology/approach:This article assesses which ChatGPT inputs(full text without tables,figures,and references;title and abstract;title only)produce better quality score estimates,and the extent to which scores are affected by ChatGPT models and system prompts.Findings:The optimal input is the article title and abstract,with average ChatGPT scores based on these(30 iterations on a dataset of 51 papers)correlating at 0.67 with human scores,the highest ever reported.ChatGPT 4o is slightly better than 3.5-turbo(0.66),and 4o-mini(0.66).Research limitations:The data is a convenience sample of the work of a single author,it only includes one field,and the scores are self-evaluations.Practical implications:The results suggest that article full texts might confuse LLM research quality evaluations,even though complex system instructions for the task are more effective than simple ones.Thus,whilst abstracts contain insufficient information for a thorough assessment of rigour,they may contain strong pointers about originality and significance.Finally,linear regression can be used to convert the model scores into the human scale scores,which is 31%more accurate than guessing.Originality/value:This is the first systematic comparison of the impact of different prompts,parameters and inputs for ChatGPT research quality evaluations.
基金supported by the National Key R&D Program of China under Grant No.2022YFB3103500the National Natural Science Foundation of China under Grants No.62402087 and No.62020106013+3 种基金the Sichuan Science and Technology Program under Grant No.2023ZYD0142the Chengdu Science and Technology Program under Grant No.2023-XT00-00002-GXthe Fundamental Research Funds for Chinese Central Universities under Grants No.ZYGX2020ZB027 and No.Y030232063003002the Postdoctoral Innovation Talents Support Program under Grant No.BX20230060.
文摘The integration of artificial intelligence(AI)technology,particularly large language models(LLMs),has become essential across various sectors due to their advanced language comprehension and generation capabilities.Despite their transformative impact in fields such as machine translation and intelligent dialogue systems,LLMs face significant challenges.These challenges include safety,security,and privacy concerns that undermine their trustworthiness and effectiveness,such as hallucinations,backdoor attacks,and privacy leakage.Previous works often conflated safety issues with security concerns.In contrast,our study provides clearer and more reasonable definitions for safety,security,and privacy within the context of LLMs.Building on these definitions,we provide a comprehensive overview of the vulnerabilities and defense mechanisms related to safety,security,and privacy in LLMs.Additionally,we explore the unique research challenges posed by LLMs and suggest potential avenues for future research,aiming to enhance the robustness and reliability of LLMs in the face of emerging threats.
文摘Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently,researchers have explored the potential of using large language models(LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.
文摘ChatGPT is a powerful artificial intelligence(AI)language model that has demonstrated significant improvements in various natural language processing(NLP) tasks. However, like any technology, it presents potential security risks that need to be carefully evaluated and addressed. In this survey, we provide an overview of the current state of research on security of using ChatGPT, with aspects of bias, disinformation, ethics, misuse,attacks and privacy. We review and discuss the literature on these topics and highlight open research questions and future directions.Through this survey, we aim to contribute to the academic discourse on AI security, enriching the understanding of potential risks and mitigations. We anticipate that this survey will be valuable for various stakeholders involved in AI development and usage, including AI researchers, developers, policy makers, and end-users.
基金the National Natural Science Foundation of China(No.52205468)China Postdoctoral Science Foundation(No.2022M710061 and No.2023T160277)Natural Science Foundation of Jiangsu Province(No.BK20210755)。
文摘Large size titanium alloy parts are widely used in aerospace.However,they are difficult to manufacture using mechanical cutting technology because of severe tool wear.Electrochemical jet machining is a promising technology to achieve high efficiency,because it has high machining flexibility and no machining tool wear.However,reports on the macro electrochemical jet machining of large size titanium alloy parts are very scarce,because it is difficult to achieve effective constraint of the flow field in macro electrochemical jet machining.In addition,titanium alloy is very sensitive to fluctuation of the flow field,and a turbulent flow field would lead to serious stray corrosion.This paper reports a series of investigations of the electrochemical jet machining of titanium alloy parts.Based on the flow analysis and experiments,the machining flow field was effectively constrained.TB6 titanium alloy part with a perimeter of one meter was machined.The machined surface was smooth with no obvious machining defects.The machining process was particularly stable with no obvious spark discharge.The research provides a reference for the application of electrochemical jet machining technology to achieve large allowance material removal in the machining of large titanium alloy parts.
基金Supported by the China Health Promotion Foundation Young Doctors'Research Foundation for Inflammatory Bowel Disease,the Taishan Scholars Program of Shandong Province,China,No.tsqn202306343National Natural Science Foundation of China,No.82270578.
文摘BACKGROUND Inflammatory bowel disease(IBD)is a global health burden that affects millions of individuals worldwide,necessitating extensive patient education.Large language models(LLMs)hold promise for addressing patient information needs.However,LLM use to deliver accurate and comprehensible IBD-related medical information has yet to be thoroughly investigated.AIM To assess the utility of three LLMs(ChatGPT-4.0,Claude-3-Opus,and Gemini-1.5-Pro)as a reference point for patients with IBD.METHODS In this comparative study,two gastroenterology experts generated 15 IBD-related questions that reflected common patient concerns.These questions were used to evaluate the performance of the three LLMs.The answers provided by each model were independently assessed by three IBD-related medical experts using a Likert scale focusing on accuracy,comprehensibility,and correlation.Simultaneously,three patients were invited to evaluate the comprehensibility of their answers.Finally,a readability assessment was performed.RESULTS Overall,each of the LLMs achieved satisfactory levels of accuracy,comprehensibility,and completeness when answering IBD-related questions,although their performance varies.All of the investigated models demonstrated strengths in providing basic disease information such as IBD definition as well as its common symptoms and diagnostic methods.Nevertheless,when dealing with more complex medical advice,such as medication side effects,dietary adjustments,and complication risks,the quality of answers was inconsistent between the LLMs.Notably,Claude-3-Opus generated answers with better readability than the other two models.CONCLUSION LLMs have the potential as educational tools for patients with IBD;however,there are discrepancies between the models.Further optimization and the development of specialized models are necessary to ensure the accuracy and safety of the information provided.
基金supported by the National Natural Science Foundation of China(Nos.52074246,52275390,52375394)the National Defense Basic Scientific Research Program of China(No.JCKY2020408B002)the Key R&D Program of Shanxi Province(No.202102050201011).
文摘The design of casting gating system directly determines the solidification sequence,defect severity,and overall quality of the casting.A novel machine learning strategy was developed to design the counter pressure casting gating system of a large thin-walled cabin casting.A high-quality dataset was established through orthogonal experiments combined with design criteria for the gating system.Spearman’s correlation analysis was used to select high-quality features.The gating system dimensions were predicted using a gated recurrent unit(GRU)recurrent neural network and an elastic network model.Using EasyCast and ProCAST casting software,a comparative analysis of the flow field,temperature field,and solidification field can be conducted to demonstrate the achievement of steady filling and top-down sequential solidification.Compared to the empirical formula method,this method eliminates trial-and-error iterations,reduces porosity,reduces casting defect volume from 11.23 cubic centimeters to 2.23 cubic centimeters,eliminates internal casting defects through the incorporation of an internally cooled iron,fulfilling the goal of intelligent gating system design.
基金National Natural Science Foundation of china(No.42371446)Natural Science Foundatiorof Hubei Province(No.2024AFD412)Fundamental Research Funds for National Universities,China University of Geosciences(Wuhan)(No.2024XLA17).
文摘In recent years,Volunteered Geographic Information(VGI)has emerged as a crucial source of mapping data,contributed by users through crowdsourcing platforms such as OpenStreetMap.This paper presents a novel approach that Integrates Large Language Models(LLMs)into a fully automated mapping workflow,utilizing VGI data.The process leverages Prompt Engineering,which involves designing and optimizing input instructions to ensure the LLM produces desired mapping outputs.By constructing precise and detailed prompts,LLM agents are able to accurately interpret mapping requirements,and autonomously extract,analyze,and process VGI geospatial data.They dynamically interact with mapping tools to automate the entire mapping process—from data acquisition to map generation.This approach significantly streamlines the creation of high-quality mapping outputs,reducing the time and resources typically required for such tasks.Moreover,the system lowers the barrier for non-expert users,enabling them to generate accurate maps without extensive technical expertise.Through various case studies,we demonstrate the LLM application across different mapping scenarios,highlighting its potential to enhance the efficiency,accuracy,and accessibility of map production.The results suggest that LLM-powered mapping systems can not only optimize VGI data processing but also expand the usability of ubiquitous mapping across diverse fields,including urban planning and infrastructure development.
基金supported by the Key Research and Development Program of Science and Technology Department of Guizhou Province(No.20204Y147).
文摘Background:The prognostic significance of the chemokine receptor CCR7 in diffuse large B-cell lymphoma(DLBCL)has been reported previously.However,the detailed mechanisms of CCR7 in DLBCL,particularly regarding its interaction with lenalidomide treatment,are not fully understood.Methods:Our study utilized bioinformatics approaches to identify hub genes in SU-DHL-2 cell lines treated with lenalidomide compared to control groups.Immunohistochemical data and clinical information from 122 patients with DLBCL were analyzed to assess the correlation of CCR7 and p-ERK1/2 expression with the prognosis of DLBCL.Furthermore,in vitro and in vivo experiments were conducted to clarify the role of CCR7 in the response of DLBCL to lenalidomide treatment.Results:Our bioinformatics analysis pinpointed CCR7 as a hub gene in the context of lenalidomide treatment in DLBCL.Notably,31.14%and 36.0%(44/122)of DLBCL cases showed positive expression for CCR7 and ERK1/2 respectively,establishing them as independent prognostic factors for adverse outcomes in DLBCL via multivariate Cox regression analysis.Additionally,our studies demonstrated that the external application of the protein CCL21 promoted proliferation,migration,invasion,and activation of the ERK1/2 pathway in SU-DHL-2 and OCI-LY3 cell lines with high levels of CCR7 expression.This effect was mitigated by CCR7 silencing through siRNA,application of ERK inhibitors,or lenalidomide treatment.In vivo experiments reinforced the efficacy of lenalidomide,significantly reducing tumor growth rate,tumor mass,serum total LDH levels,and expression of CCR7 and p-ERK1/2 in a SUDHL-2 xenograft model in nude mice(p<0.05).Conclusion:Our study clarifies the potential role of the CCL21/CCR7/ERK1/2 axis in the therapeutic effects of lenalidomide in DLBCL treatment.
文摘Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.
文摘The rapid advancement of Artificial Intelligence(AI)and Large Language Models(LLMs)has led to their increasing integration into various domains,from text generation and translation to question-answering.However,a critical question remains:do these sophisticated models,much like humans,exhibit susceptibility to cognitive biases?Understanding the presence and nature of such biases in AI is paramount for assessing their reliability,enhancing their performance,and predicting their societal impact.This research specifically investigates the susceptibility of Google’s Gemini 1.5 Pro and DeepSeek,two prominent LLMs,to framing effects and confirmation bias.The study meticulously designed a series of experimental trials,systematically manipulating information proportions and presentation orders to evaluate these biases.In the framing effect experiment,a genetic testing decision-making scenario was constructed.The proportion of positive and negative information(e.g.,20%,50%,or 80%positive)and their presentation order were varied.The models’inclination towards undergoing genetic testing was recorded.For the confirmation bias experiment,two reports-one positive and one negative-about“RoboTaxi”autonomous vehicles were provided.The proportion of erroneous information within these reports(10%,30%,and 50%)and their presentation order were systematically altered,and the models’support for each report was assessed.The findings demonstrate that both Gemini 1.5 Pro and DeepSeek are susceptible to framing effects.In the genetic testing scenario,their decision-making was primarily influenced by the proportion of positive and negative information presented.When the proportion of positive information was higher,both models showed a greater inclination to recommend or proceed with genetic testing.Conversely,a higher proportion of negative information led to greater caution or a tendency not to recommend the testing.Importantly,the order in which this information was presented did not significantly influence their decisions in the framing effect scenarios.Regarding confirmation bias,the two models exhibited distinct behaviors.Gemini 1.5 Pro did not show an overall preference for either positive or negative reports.However,its judgments were significantly influenced by the order of information presentation,demonstrating a“recency effect,”meaning it tended to support the report presented later.The proportion of erroneous information within the reports had no significant impact on Gemini 1.5 Pro’s decisions.In contrast,DeepSeek exhibited an overall confirmation bias,showing a clear preference for positive reports.Similar to Gemini 1.5 Pro,DeepSeek’s decisions were also significantly affected by the order of information presentation,while the proportion of misinformation had no significant effect.These results reveal human-like cognitive vulnerabilities in advanced LLMs,highlighting critical challenges to their reliability and objectivity in decision-making processes.Gemini 1.5 Pro’s sensitivity to presentation order and DeepSeek’s general preference for positive information,coupled with its sensitivity to order,underscore the need for careful evaluation of potential cognitive biases during the development and application of AI.The study suggests that effective measures are necessary to mitigate these biases and prevent potential negative societal impacts.Future research should include a broader range of models for comparative analysis and explore more complex interactive scenarios to further understand and address these phenomena.The findings contribute significantly to understanding the limitations and capabilities of current AI systems,guiding their responsible development,and anticipating their potential societal implications.
文摘We study the two-dimensional(2D)Cauchy problem of nonhomogeneous Boussinesq system for magnetohydrodynamics convection without heat diffusion in the whole plane.Based on delicate weighted estimates,we derive the global existence and uniqueness of strong solutions.In particular,the initial data can be arbitrarily large and the initial density may contain vacuum states and even have compact support.
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.
文摘Smart contracts on the Ethereum blockchain continue to revolutionize decentralized applications (dApps) by allowing for self-executing agreements. However, bad actors have continuously found ways to exploit smart contracts for personal financial gain, which undermines the integrity of the Ethereum blockchain. This paper proposes a computer program called SADA (Static and Dynamic Analyzer), a novel approach to smart contract vulnerability detection using multiple Large Language Model (LLM) agents to analyze and flag suspicious Solidity code for Ethereum smart contracts. SADA not only improves upon existing vulnerability detection methods but also paves the way for more secure smart contract development practices in the rapidly evolving blockchain ecosystem.
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co-supported by the National Natural Science Foundation of China(Nos.52472394,52425211,52201327,52272360)。
文摘Stall flutter poses great challenges to flight safety.To alleviate this problem,a steady blowing control considering the perturbation and wake-induced vibration at a large angle of attack is developed in this paper,where two blowings are configured on upper and lower tail surfaces to suppress the stall flutter.The stall flutter with one-degree-of-freedom is first evaluated by numerical simulation.The equation of motion for stall flutter is solved by the Newmark-β method.Then,the stall flutter responses for five blowing speeds,i.e.,0,4,12,20,and 28 m/s under the airspeed range of 3–9 m/s,are studied in detail.The stall flutter suppression mechanism can be summarized as follows:a large blowing speed can inject energy into the boundary layer and enhance the high-pressure zone,which delays the flow separation on the suction surface.In this way,the formation of the leading-edge separation vortex is suppressed.Thus,the dynamic stall vortex is weakened and accelerates shedding.In addition,the driving moment is reduced,which leads to a decrement in the stall flutter amplitude.When the blowing speed is 28 m/s(stall flutter amplitude=0.1357 rad),compared with uncontrolled case(stall flutter amplitude=0.6002 rad),the amplitude can decrease by 77.39%,which demonstrates the effectiveness of the proposed steady blowing based active control strategy.
基金supported by the Natural Science Foundation of Hunan Province of China(No.2023JJ40672)the Innovation Science Fund Project of National University of Defense Technology,China(No.ZK2023-039)。
文摘A two-dimensional large eddy simulation numerical model is proposed to study the transient vortex flow and pressure oscillation of a large-aspect-ratio solid rocket motor.The numerical model is validated through experimental data,finite element analysis and cumulative error analysis.The numerical simulations are executed to obtain the characteristics of the vortex-acoustic and pressure oscillation.The results show that the burning surface regression decreases the motor aspect ratio,increasing the corresponding natural frequency from 260 Hz to 293 Hz.The pressure oscillation phenomenon is formed due to the vortex-acoustic coupling.Decreasing the corner vortex shedding intensity shows negative effects on the dimensionless amplitude of the pressure oscillation.The head cavity without the injection can decrease the vortex-acoustic coupling level at the acoustic pressure antinode.The modified motor with head cavity can obtain a lower dimensionless oscillating pressure amplitude 0.00149 in comparison with 0.00895 of the original motor.The aspect ratio and volume of the head cavity without the injection have great effects on the pressure oscillation suppression,particularly at the low aspect ratio or large volume.The reason is that the mass in the region around the acoustic pressure antinode is extracted centrally,reducing the energy contribution to the acoustic system.With the volume increasing,the acoustic energy capacity increases.
