Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in speci...Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader deployment.Parameter-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational efficiency.Among these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA variants.Despite these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains underexplored.This study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM architectures.Our investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do so.These insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized LLMs.Moreover,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller one.This study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM fine-tuning in resource-constrained environments.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
With the deepening of cross-cultural educational cooperation between China and Malaysia,the cross-cultural challenges that Chinese overseas students face in Malaysia due to language and cultural differences have becom...With the deepening of cross-cultural educational cooperation between China and Malaysia,the cross-cultural challenges that Chinese overseas students face in Malaysia due to language and cultural differences have become increasingly prominent.Focusing on Chinese graduate students at a public university in Malaysia where English is the medium of instruction,this study employs a scale survey method in conjunction with IBM SPSS 26.0 and Smart PLS 4.0 for data analysis to quantitatively explore the level of language anxiety and its relationship with cross-cultural adaptability and learning motivation.The results indicate that most Chinese graduate students experience notable language anxiety,which is significantly negatively correlated with cross-cultural adaptability,especially academic adaptability,but is not related to learning motivation.Furthermore,the study reveals the complex influencing mechanism of language anxiety within multicultural educational environments and offers suggestions for improvement tailored to Malaysia’s unique educational context.These include utilizing technological tools for language interventions,optimizing classroom teaching strategies,enhancing language learning motivation through external incentives,strengthening training for cross-cultural adaptation skills,and promoting deeper cross-cultural communication.This study provides theoretical support and practical references for alleviating language anxiety and enhancing the cross-cultural adaptability of Chinese overseas students.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
The advent of large language models(LLMs)has made knowledge acquisition and content creation increasingly easier and cheaper,which in turn redefines learning and urges transformation in software engineering education....The advent of large language models(LLMs)has made knowledge acquisition and content creation increasingly easier and cheaper,which in turn redefines learning and urges transformation in software engineering education.To do so,there is a need to understand the impact of LLMs on software engineering education.In this paper,we conducted a preliminary case study on three software requirements engineering classes where students are allowed to use LLMs to assist in their projects.Based on the students’experience,performance,and feedback from a survey conducted at the end of the courses,we characterized the challenges and benefits of applying LLMs in software engineering education.This research contributes to the ongoing discourse on the integration of LLMs in education,emphasizing both their prominent potential and the need for balanced,mindful usage.展开更多
Assessment is a crucial aspect of the teaching process for teachers.Teachers’assessment literacy is closely related to students’learning outcomes.The language assessment literacy of foreign language teachers is a si...Assessment is a crucial aspect of the teaching process for teachers.Teachers’assessment literacy is closely related to students’learning outcomes.The language assessment literacy of foreign language teachers is a significant component of both teachers’professional development and students’learning,and it has become a research hotspot in the field of domestic language testing.Based on clarifying the theoretical framework of language assessment literacy,this paper proposes the main cultivation paths for pre-service English teachers’language assessment literacy,aiming to provide inspiration and references for the cultivation,reform,and development of teachers in basic foreign language education.展开更多
AIM:To assess the possibility of using different large language models(LLMs)in ocular surface diseases by selecting five different LLMS to test their accuracy in answering specialized questions related to ocular surfa...AIM:To assess the possibility of using different large language models(LLMs)in ocular surface diseases by selecting five different LLMS to test their accuracy in answering specialized questions related to ocular surface diseases:ChatGPT-4,ChatGPT-3.5,Claude 2,PaLM2,and SenseNova.METHODS:A group of experienced ophthalmology professors were asked to develop a 100-question singlechoice question on ocular surface diseases designed to assess the performance of LLMs and human participants in answering ophthalmology specialty exam questions.The exam includes questions on the following topics:keratitis disease(20 questions),keratoconus,keratomalaciac,corneal dystrophy,corneal degeneration,erosive corneal ulcers,and corneal lesions associated with systemic diseases(20 questions),conjunctivitis disease(20 questions),trachoma,pterygoid and conjunctival tumor diseases(20 questions),and dry eye disease(20 questions).Then the total score of each LLMs and compared their mean score,mean correlation,variance,and confidence were calculated.RESULTS:GPT-4 exhibited the highest performance in terms of LLMs.Comparing the average scores of the LLMs group with the four human groups,chief physician,attending physician,regular trainee,and graduate student,it was found that except for ChatGPT-4,the total score of the rest of the LLMs is lower than that of the graduate student group,which had the lowest score in the human group.Both ChatGPT-4 and PaLM2 were more likely to give exact and correct answers,giving very little chance of an incorrect answer.ChatGPT-4 showed higher credibility when answering questions,with a success rate of 59%,but gave the wrong answer to the question 28% of the time.CONCLUSION:GPT-4 model exhibits excellent performance in both answer relevance and confidence.PaLM2 shows a positive correlation(up to 0.8)in terms of answer accuracy during the exam.In terms of answer confidence,PaLM2 is second only to GPT4 and surpasses Claude 2,SenseNova,and GPT-3.5.Despite the fact that ocular surface disease is a highly specialized discipline,GPT-4 still exhibits superior performance,suggesting that its potential and ability to be applied in this field is enormous,perhaps with the potential to be a valuable resource for medical students and clinicians in the future.展开更多
Cardiac rehabilitation is a crucial multidisciplinary approach to improve patient outcomes.There is a growing body of evidence that suggests that these programs contribute towards reducing cardiovascular mortality and...Cardiac rehabilitation is a crucial multidisciplinary approach to improve patient outcomes.There is a growing body of evidence that suggests that these programs contribute towards reducing cardiovascular mortality and recurrence.Despite this,cardiac rehabilitation is underutilized and adherence to these programs has been a demonstrated barrier in achieving these outcomes.As a result,there is a growing focus on innovating these programs,especially from the standpoint of digital health and personalized medicine.This editorial discusses the possible roles of large language models,such as their role in ChatGPT,in further personalizing cardiac rehabilitation programs through simplifying medical jargon and employing motivational interviewing techniques,thus boosting patient engagement and adherence.However,these possibilities must be further investigated in the clinical literature.Likewise,the integration of large language models in cardiac rehabilitation will be challenging in its nascent stages to ensure accurate and ethical information delivery.展开更多
This paper selects the widely used New Practical Chinese Readers,a comprehensive teaching material for Chinese as a foreign language,analyzing its content selection,presentation format,and organizational characteristi...This paper selects the widely used New Practical Chinese Readers,a comprehensive teaching material for Chinese as a foreign language,analyzing its content selection,presentation format,and organizational characteristics.By reviewing the inclusion of Chinese opera cultural elements in this material,the study identifies existing issues and provides recommendations for improvement.Introducing opera culture into Chinese language teaching materials can align with global cultural exchanges,helping more people learn about traditional Chinese culture and enhancing China’s international influence.展开更多
Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language intelligence.Language modeling,crucial for AI development,has evolved from statistical to neural models over the ...Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language intelligence.Language modeling,crucial for AI development,has evolved from statistical to neural models over the last two decades.Recently,transformer-based Pre-trained Language Models(PLM)have excelled in Natural Language Processing(NLP)tasks by leveraging large-scale training corpora.Increasing the scale of these models enhances performance significantly,introducing abilities like context learning that smaller models lack.The advancement in Large Language Models,exemplified by the development of ChatGPT,has made significant impacts both academically and industrially,capturing widespread societal interest.This survey provides an overview of the development and prospects from Large Language Models(LLM)to Large Multimodal Models(LMM).It first discusses the contributions and technological advancements of LLMs in the field of natural language processing,especially in text generation and language understanding.Then,it turns to the discussion of LMMs,which integrates various data modalities such as text,images,and sound,demonstrating advanced capabilities in understanding and generating cross-modal content,paving new pathways for the adaptability and flexibility of AI systems.Finally,the survey highlights the prospects of LMMs in terms of technological development and application potential,while also pointing out challenges in data integration,cross-modal understanding accuracy,providing a comprehensive perspective on the latest developments in this field.展开更多
The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Infor...The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Information (PII) and other confidential or protected information that may have been memorized during training, specifically during a fine-tuning or customization process. We describe different black-box attacks from potential adversaries and study their impact on the amount and type of information that may be recovered from commonly used and deployed LLMs. Our research investigates the relationship between PII leakage, memorization, and factors such as model size, architecture, and the nature of attacks employed. The study utilizes two broad categories of attacks: PII leakage-focused attacks (auto-completion and extraction attacks) and memorization-focused attacks (various membership inference attacks). The findings from these investigations are quantified using an array of evaluative metrics, providing a detailed understanding of LLM vulnerabilities and the effectiveness of different attacks.展开更多
Deaf people or people facing hearing issues can communicate using sign language(SL),a visual language.Many works based on rich source language have been proposed;however,the work using poor resource language is still ...Deaf people or people facing hearing issues can communicate using sign language(SL),a visual language.Many works based on rich source language have been proposed;however,the work using poor resource language is still lacking.Unlike other SLs,the visuals of the Urdu Language are different.This study presents a novel approach to translating Urdu sign language(UrSL)using the UrSL-CNN model,a convolutional neural network(CNN)architecture specifically designed for this purpose.Unlike existingworks that primarily focus on languageswith rich resources,this study addresses the challenge of translating a sign language with limited resources.We conducted experiments using two datasets containing 1500 and 78,000 images,employing a methodology comprising four modules:data collection,pre-processing,categorization,and prediction.To enhance prediction accuracy,each sign image was transformed into a greyscale image and underwent noise filtering.Comparative analysis with machine learning baseline methods(support vectormachine,GaussianNaive Bayes,randomforest,and k-nearest neighbors’algorithm)on the UrSL alphabets dataset demonstrated the superiority of UrSL-CNN,achieving an accuracy of 0.95.Additionally,our model exhibited superior performance in Precision,Recall,and F1-score evaluations.This work not only contributes to advancing sign language translation but also holds promise for improving communication accessibility for individuals with hearing impairments.展开更多
Objective:Despite the decrease in the number of foreign visitors and residents in Japan due to the coronavirus disease 2019,a resurgence is remarkable from 2022.However,Japan's medical support system for foreign p...Objective:Despite the decrease in the number of foreign visitors and residents in Japan due to the coronavirus disease 2019,a resurgence is remarkable from 2022.However,Japan's medical support system for foreign patients,especially residents,is inadequate,with language barriers potentially causing health disparities.Comprehensive interpretation and translation services are challenging,but“plain Japanese”may be a viable alternative for foreign patients with basic Japanese language skills.This study explores the application and obstacles of plain Japanese in the medical sector.Methods:A literature review was performed across these databases:Web of Science,PubMed,Google Scholar,Scopus,CINAHL Plus,Springer Link and Ichushi-Web(Japanese medical literature).The search covered themes related to healthcare,care for foreign patients,and scholarly articles,and was conducted in July 2023.Results:The study incorporated five papers.Each paper emphasized the language barriers foreign residents in Japan face when accessing healthcare,highlighting the critical role and necessity of plain Japanese in medical environments.Most of the reports focused on the challenges of delivering medical care to foreign patients and the training of healthcare professionals in using plain Japanese for communication.Conclusion:The knowledge and application of plain Japanese among healthcare professionals are inadequate,and literature also remains scarce.With the increasing number of foreign residents in Japan,the establishment of a healthcare system that effectively uses plain Japanese is essential.However,plain Japanese may not be the optimal linguistic assistance in certain situations,thus it is imperative to encourage more research and reports on healthcare services using plain Japanese.展开更多
Foreign language teaching practice is developing rapidly,but research on foreign language teacher learning is currently relatively fragmented and unstructured.The book Foreign Language Teacher Learning,written by Prof...Foreign language teaching practice is developing rapidly,but research on foreign language teacher learning is currently relatively fragmented and unstructured.The book Foreign Language Teacher Learning,written by Professor Kang Yan from Capital Normal University,published in September 2022,makes a systematic introduction to foreign language teacher learning,which to some extent makes up for this shortcoming.Her book presents the lineage of foreign language teacher learning research at home and abroad,analyzes both theoretical and practical aspects,reviews the cuttingedge research results,and foresees the future development trend,painting a complete research picture for researchers in the field of foreign language teaching and teacher education as well as front-line teachers interested in foreign language teacher learning.This is an important inspiration for conducting foreign language teacher learning research in the future.And this paper makes a review of the book from aspects such as its content,major characteristics,contributions and limitations.展开更多
The exponential growth of literature is constraining researchers’access to comprehensive information in related fields.While natural language processing(NLP)may offer an effective solution to literature classificatio...The exponential growth of literature is constraining researchers’access to comprehensive information in related fields.While natural language processing(NLP)may offer an effective solution to literature classification,it remains hindered by the lack of labelled dataset.In this article,we introduce a novel method for generating literature classification models through semi-supervised learning,which can generate labelled dataset iteratively with limited human input.We apply this method to train NLP models for classifying literatures related to several research directions,i.e.,battery,superconductor,topological material,and artificial intelligence(AI)in materials science.The trained NLP‘battery’model applied on a larger dataset different from the training and testing dataset can achieve F1 score of 0.738,which indicates the accuracy and reliability of this scheme.Furthermore,our approach demonstrates that even with insufficient data,the not-well-trained model in the first few cycles can identify the relationships among different research fields and facilitate the discovery and understanding of interdisciplinary directions.展开更多
In response to the challenges of generating Attribute-Based Access Control(ABAC)policies,this paper proposes a deep learning-based method to automatically generate ABAC policies from natural language documents.This me...In response to the challenges of generating Attribute-Based Access Control(ABAC)policies,this paper proposes a deep learning-based method to automatically generate ABAC policies from natural language documents.This method is aimed at organizations such as companies and schools that are transitioning from traditional access control models to the ABAC model.The manual retrieval and analysis involved in this transition are inefficient,prone to errors,and costly.Most organizations have high-level specifications defined for security policies that include a set of access control policies,which often exist in the form of natural language documents.Utilizing this rich source of information,our method effectively identifies and extracts the necessary attributes and rules for access control from natural language documents,thereby constructing and optimizing access control policies.This work transforms the problem of policy automation generation into two tasks:extraction of access control statements andmining of access control attributes.First,the Chat General Language Model(ChatGLM)isemployed to extract access control-related statements from a wide range of natural language documents by constructing unique prompts and leveraging the model’s In-Context Learning to contextualize the statements.Then,the Iterated Dilated-Convolutions-Conditional Random Field(ID-CNN-CRF)model is used to annotate access control attributes within these extracted statements,including subject attributes,object attributes,and action attributes,thus reassembling new access control policies.Experimental results show that our method,compared to baseline methods,achieved the highest F1 score of 0.961,confirming the model’s effectiveness and accuracy.展开更多
Declining cognitive abilities can be a concomitant of advanced age.As language is closely associated with cognitive abilities,changes in language abilities can be an important marker of changes in cognitive abilities....Declining cognitive abilities can be a concomitant of advanced age.As language is closely associated with cognitive abilities,changes in language abilities can be an important marker of changes in cognitive abilities.The current study is to review cognitive studies of language and aging by first identifying and exploring the major clusters and pivotal articles and then detecting emerging trends.Data of 3,266 articles on language and aging from 2013 to 2022 were collected from the Web of Science Core Collection database.Adopting Document Co-citation Analysis,Freeman’s betweenness centrality metric(Freeman,2002)and Kleinberg’s burst detection algorithm(Kleinberg,2002),we explored major clusters,pivotal articles and emerging trends in this field.Cognition appears to be the most remarkable cluster.Bilingualism,speech production,listening effort,and reading comprehension are other major active clusters in a certain period.The most recent active cluster concerns the studies of Alzheimer’s disease.Articles serving as pivotal points concentrate on cognitive studies of the Framework for Understanding Effortful Listening(FUEL),the new Ease of Language Understanding model(EUL)and a hierarchical multi-representational generative framework of language comprehension.The progress in statistical methods,the relationship between language and cognitive impairment and the relationship between language abilities and cognition are the emerging trends.These emerging trends will provide some insights into how cognitive abilities influence language abilities in aging.展开更多
Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning...Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.展开更多
Modern technological advancements have made social media an essential component of daily life.Social media allow individuals to share thoughts,emotions,and ideas.Sentiment analysis plays the function of evaluating whe...Modern technological advancements have made social media an essential component of daily life.Social media allow individuals to share thoughts,emotions,and ideas.Sentiment analysis plays the function of evaluating whether the sentiment of the text is positive,negative,neutral,or any other personal emotion to understand the sentiment context of the text.Sentiment analysis is essential in business and society because it impacts strategic decision-making.Sentiment analysis involves challenges due to lexical variation,an unlabeled dataset,and text distance correlations.The execution time increases due to the sequential processing of the sequence models.However,the calculation times for the Transformer models are reduced because of the parallel processing.This study uses a hybrid deep learning strategy to combine the strengths of the Transformer and Sequence models while ignoring their limitations.In particular,the proposed model integrates the Decoding-enhanced with Bidirectional Encoder Representations from Transformers(BERT)attention(DeBERTa)and the Gated Recurrent Unit(GRU)for sentiment analysis.Using the Decoding-enhanced BERT technique,the words are mapped into a compact,semantic word embedding space,and the Gated Recurrent Unit model can capture the distance contextual semantics correctly.The proposed hybrid model achieves F1-scores of 97%on the Twitter Large Language Model(LLM)dataset,which is much higher than the performance of new techniques.展开更多
Objective This study aimed to evaluate and compare the effectiveness of knowledge base-optimized and unoptimized large language models(LLMs)in the field of orthopedics to explore optimization strategies for the applic...Objective This study aimed to evaluate and compare the effectiveness of knowledge base-optimized and unoptimized large language models(LLMs)in the field of orthopedics to explore optimization strategies for the application of LLMs in specific fields.Methods This research constructed a specialized knowledge base using clinical guidelines from the American Academy of Orthopaedic Surgeons(AAOS)and authoritative orthopedic publications.A total of 30 orthopedic-related questions covering aspects such as anatomical knowledge,disease diagnosis,fracture classification,treatment options,and surgical techniques were input into both the knowledge base-optimized and unoptimized versions of the GPT-4,ChatGLM,and Spark LLM,with their generated responses recorded.The overall quality,accuracy,and comprehensiveness of these responses were evaluated by 3 experienced orthopedic surgeons.Results Compared with their unoptimized LLMs,the optimized version of GPT-4 showed improvements of 15.3%in overall quality,12.5%in accuracy,and 12.8%in comprehensiveness;ChatGLM showed improvements of 24.8%,16.1%,and 19.6%,respectively;and Spark LLM showed improvements of 6.5%,14.5%,and 24.7%,respectively.Conclusion The optimization of knowledge bases significantly enhances the quality,accuracy,and comprehensiveness of the responses provided by the 3 models in the orthopedic field.Therefore,knowledge base optimization is an effective method for improving the performance of LLMs in specific fields.展开更多
基金supported by the National Key R&D Program of China(No.2021YFB0301200)National Natural Science Foundation of China(No.62025208).
文摘Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader deployment.Parameter-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational efficiency.Among these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA variants.Despite these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains underexplored.This study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM architectures.Our investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do so.These insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized LLMs.Moreover,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller one.This study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM fine-tuning in resource-constrained environments.
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.
基金funded by the 2022 Annual Key Research Project on Theoretical and Practical Studies of Ideological and Political Education for University Students in GuangxiSpecial Focus on University Counselors:Exploration and Practice of a Cultivation Ecosystem for Cultivating Both Moral Character and Talent Through “One Virtue+Two Lines+Three Stages+Four Micro-Education Methods” for Ideological and Political Education in Universities from the Perspective of Peer Language Systems,Project No.:2022MSZ031
文摘With the deepening of cross-cultural educational cooperation between China and Malaysia,the cross-cultural challenges that Chinese overseas students face in Malaysia due to language and cultural differences have become increasingly prominent.Focusing on Chinese graduate students at a public university in Malaysia where English is the medium of instruction,this study employs a scale survey method in conjunction with IBM SPSS 26.0 and Smart PLS 4.0 for data analysis to quantitatively explore the level of language anxiety and its relationship with cross-cultural adaptability and learning motivation.The results indicate that most Chinese graduate students experience notable language anxiety,which is significantly negatively correlated with cross-cultural adaptability,especially academic adaptability,but is not related to learning motivation.Furthermore,the study reveals the complex influencing mechanism of language anxiety within multicultural educational environments and offers suggestions for improvement tailored to Malaysia’s unique educational context.These include utilizing technological tools for language interventions,optimizing classroom teaching strategies,enhancing language learning motivation through external incentives,strengthening training for cross-cultural adaptation skills,and promoting deeper cross-cultural communication.This study provides theoretical support and practical references for alleviating language anxiety and enhancing the cross-cultural adaptability of Chinese overseas students.
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.
基金supported in part by the Teaching Reform Project of Chongqing University of Posts and Telecommunications,China under Grant No.XJG23234Chongqing Municipal Higher Education Teaching Reform Research Project under Grant No.203399the Doctoral Direct Train Project of Chongqing Science and Technology Bureau under Grant No.CSTB2022BSXM-JSX0007。
文摘The advent of large language models(LLMs)has made knowledge acquisition and content creation increasingly easier and cheaper,which in turn redefines learning and urges transformation in software engineering education.To do so,there is a need to understand the impact of LLMs on software engineering education.In this paper,we conducted a preliminary case study on three software requirements engineering classes where students are allowed to use LLMs to assist in their projects.Based on the students’experience,performance,and feedback from a survey conducted at the end of the courses,we characterized the challenges and benefits of applying LLMs in software engineering education.This research contributes to the ongoing discourse on the integration of LLMs in education,emphasizing both their prominent potential and the need for balanced,mindful usage.
基金2021 Young Teacher Research Funding Project of Hubei Normal University(HS2021QN014)。
文摘Assessment is a crucial aspect of the teaching process for teachers.Teachers’assessment literacy is closely related to students’learning outcomes.The language assessment literacy of foreign language teachers is a significant component of both teachers’professional development and students’learning,and it has become a research hotspot in the field of domestic language testing.Based on clarifying the theoretical framework of language assessment literacy,this paper proposes the main cultivation paths for pre-service English teachers’language assessment literacy,aiming to provide inspiration and references for the cultivation,reform,and development of teachers in basic foreign language education.
基金Supported by National Natural Science Foundation of China(No.82160195,No.82460203)Degree and Postgraduate Education Teaching Reform Project of Jiangxi Province(No.JXYJG-2020-026).
文摘AIM:To assess the possibility of using different large language models(LLMs)in ocular surface diseases by selecting five different LLMS to test their accuracy in answering specialized questions related to ocular surface diseases:ChatGPT-4,ChatGPT-3.5,Claude 2,PaLM2,and SenseNova.METHODS:A group of experienced ophthalmology professors were asked to develop a 100-question singlechoice question on ocular surface diseases designed to assess the performance of LLMs and human participants in answering ophthalmology specialty exam questions.The exam includes questions on the following topics:keratitis disease(20 questions),keratoconus,keratomalaciac,corneal dystrophy,corneal degeneration,erosive corneal ulcers,and corneal lesions associated with systemic diseases(20 questions),conjunctivitis disease(20 questions),trachoma,pterygoid and conjunctival tumor diseases(20 questions),and dry eye disease(20 questions).Then the total score of each LLMs and compared their mean score,mean correlation,variance,and confidence were calculated.RESULTS:GPT-4 exhibited the highest performance in terms of LLMs.Comparing the average scores of the LLMs group with the four human groups,chief physician,attending physician,regular trainee,and graduate student,it was found that except for ChatGPT-4,the total score of the rest of the LLMs is lower than that of the graduate student group,which had the lowest score in the human group.Both ChatGPT-4 and PaLM2 were more likely to give exact and correct answers,giving very little chance of an incorrect answer.ChatGPT-4 showed higher credibility when answering questions,with a success rate of 59%,but gave the wrong answer to the question 28% of the time.CONCLUSION:GPT-4 model exhibits excellent performance in both answer relevance and confidence.PaLM2 shows a positive correlation(up to 0.8)in terms of answer accuracy during the exam.In terms of answer confidence,PaLM2 is second only to GPT4 and surpasses Claude 2,SenseNova,and GPT-3.5.Despite the fact that ocular surface disease is a highly specialized discipline,GPT-4 still exhibits superior performance,suggesting that its potential and ability to be applied in this field is enormous,perhaps with the potential to be a valuable resource for medical students and clinicians in the future.
文摘Cardiac rehabilitation is a crucial multidisciplinary approach to improve patient outcomes.There is a growing body of evidence that suggests that these programs contribute towards reducing cardiovascular mortality and recurrence.Despite this,cardiac rehabilitation is underutilized and adherence to these programs has been a demonstrated barrier in achieving these outcomes.As a result,there is a growing focus on innovating these programs,especially from the standpoint of digital health and personalized medicine.This editorial discusses the possible roles of large language models,such as their role in ChatGPT,in further personalizing cardiac rehabilitation programs through simplifying medical jargon and employing motivational interviewing techniques,thus boosting patient engagement and adherence.However,these possibilities must be further investigated in the clinical literature.Likewise,the integration of large language models in cardiac rehabilitation will be challenging in its nascent stages to ensure accurate and ethical information delivery.
基金Zhejiang Federation of Humanities and Social Sciences Circles“Investigating the Effect of ChatGPT on L2 Education”(24NDQN206YBM)。
文摘This paper selects the widely used New Practical Chinese Readers,a comprehensive teaching material for Chinese as a foreign language,analyzing its content selection,presentation format,and organizational characteristics.By reviewing the inclusion of Chinese opera cultural elements in this material,the study identifies existing issues and provides recommendations for improvement.Introducing opera culture into Chinese language teaching materials can align with global cultural exchanges,helping more people learn about traditional Chinese culture and enhancing China’s international influence.
基金We acknowledge funding from NSFC Grant 62306283.
文摘Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language intelligence.Language modeling,crucial for AI development,has evolved from statistical to neural models over the last two decades.Recently,transformer-based Pre-trained Language Models(PLM)have excelled in Natural Language Processing(NLP)tasks by leveraging large-scale training corpora.Increasing the scale of these models enhances performance significantly,introducing abilities like context learning that smaller models lack.The advancement in Large Language Models,exemplified by the development of ChatGPT,has made significant impacts both academically and industrially,capturing widespread societal interest.This survey provides an overview of the development and prospects from Large Language Models(LLM)to Large Multimodal Models(LMM).It first discusses the contributions and technological advancements of LLMs in the field of natural language processing,especially in text generation and language understanding.Then,it turns to the discussion of LMMs,which integrates various data modalities such as text,images,and sound,demonstrating advanced capabilities in understanding and generating cross-modal content,paving new pathways for the adaptability and flexibility of AI systems.Finally,the survey highlights the prospects of LMMs in terms of technological development and application potential,while also pointing out challenges in data integration,cross-modal understanding accuracy,providing a comprehensive perspective on the latest developments in this field.
文摘The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Information (PII) and other confidential or protected information that may have been memorized during training, specifically during a fine-tuning or customization process. We describe different black-box attacks from potential adversaries and study their impact on the amount and type of information that may be recovered from commonly used and deployed LLMs. Our research investigates the relationship between PII leakage, memorization, and factors such as model size, architecture, and the nature of attacks employed. The study utilizes two broad categories of attacks: PII leakage-focused attacks (auto-completion and extraction attacks) and memorization-focused attacks (various membership inference attacks). The findings from these investigations are quantified using an array of evaluative metrics, providing a detailed understanding of LLM vulnerabilities and the effectiveness of different attacks.
文摘Deaf people or people facing hearing issues can communicate using sign language(SL),a visual language.Many works based on rich source language have been proposed;however,the work using poor resource language is still lacking.Unlike other SLs,the visuals of the Urdu Language are different.This study presents a novel approach to translating Urdu sign language(UrSL)using the UrSL-CNN model,a convolutional neural network(CNN)architecture specifically designed for this purpose.Unlike existingworks that primarily focus on languageswith rich resources,this study addresses the challenge of translating a sign language with limited resources.We conducted experiments using two datasets containing 1500 and 78,000 images,employing a methodology comprising four modules:data collection,pre-processing,categorization,and prediction.To enhance prediction accuracy,each sign image was transformed into a greyscale image and underwent noise filtering.Comparative analysis with machine learning baseline methods(support vectormachine,GaussianNaive Bayes,randomforest,and k-nearest neighbors’algorithm)on the UrSL alphabets dataset demonstrated the superiority of UrSL-CNN,achieving an accuracy of 0.95.Additionally,our model exhibited superior performance in Precision,Recall,and F1-score evaluations.This work not only contributes to advancing sign language translation but also holds promise for improving communication accessibility for individuals with hearing impairments.
文摘Objective:Despite the decrease in the number of foreign visitors and residents in Japan due to the coronavirus disease 2019,a resurgence is remarkable from 2022.However,Japan's medical support system for foreign patients,especially residents,is inadequate,with language barriers potentially causing health disparities.Comprehensive interpretation and translation services are challenging,but“plain Japanese”may be a viable alternative for foreign patients with basic Japanese language skills.This study explores the application and obstacles of plain Japanese in the medical sector.Methods:A literature review was performed across these databases:Web of Science,PubMed,Google Scholar,Scopus,CINAHL Plus,Springer Link and Ichushi-Web(Japanese medical literature).The search covered themes related to healthcare,care for foreign patients,and scholarly articles,and was conducted in July 2023.Results:The study incorporated five papers.Each paper emphasized the language barriers foreign residents in Japan face when accessing healthcare,highlighting the critical role and necessity of plain Japanese in medical environments.Most of the reports focused on the challenges of delivering medical care to foreign patients and the training of healthcare professionals in using plain Japanese for communication.Conclusion:The knowledge and application of plain Japanese among healthcare professionals are inadequate,and literature also remains scarce.With the increasing number of foreign residents in Japan,the establishment of a healthcare system that effectively uses plain Japanese is essential.However,plain Japanese may not be the optimal linguistic assistance in certain situations,thus it is imperative to encourage more research and reports on healthcare services using plain Japanese.
文摘Foreign language teaching practice is developing rapidly,but research on foreign language teacher learning is currently relatively fragmented and unstructured.The book Foreign Language Teacher Learning,written by Professor Kang Yan from Capital Normal University,published in September 2022,makes a systematic introduction to foreign language teacher learning,which to some extent makes up for this shortcoming.Her book presents the lineage of foreign language teacher learning research at home and abroad,analyzes both theoretical and practical aspects,reviews the cuttingedge research results,and foresees the future development trend,painting a complete research picture for researchers in the field of foreign language teaching and teacher education as well as front-line teachers interested in foreign language teacher learning.This is an important inspiration for conducting foreign language teacher learning research in the future.And this paper makes a review of the book from aspects such as its content,major characteristics,contributions and limitations.
基金funded by the Informatization Plan of Chinese Academy of Sciences(Grant No.CASWX2021SF-0102)the National Key R&D Program of China(Grant Nos.2022YFA1603903,2022YFA1403800,and 2021YFA0718700)+1 种基金the National Natural Science Foundation of China(Grant Nos.11925408,11921004,and 12188101)the Chinese Academy of Sciences(Grant No.XDB33000000)。
文摘The exponential growth of literature is constraining researchers’access to comprehensive information in related fields.While natural language processing(NLP)may offer an effective solution to literature classification,it remains hindered by the lack of labelled dataset.In this article,we introduce a novel method for generating literature classification models through semi-supervised learning,which can generate labelled dataset iteratively with limited human input.We apply this method to train NLP models for classifying literatures related to several research directions,i.e.,battery,superconductor,topological material,and artificial intelligence(AI)in materials science.The trained NLP‘battery’model applied on a larger dataset different from the training and testing dataset can achieve F1 score of 0.738,which indicates the accuracy and reliability of this scheme.Furthermore,our approach demonstrates that even with insufficient data,the not-well-trained model in the first few cycles can identify the relationships among different research fields and facilitate the discovery and understanding of interdisciplinary directions.
基金supported by the National Natural Science Foundation of China Project(No.62302540),please visit their website at https://www.nsfc.gov.cn/(accessed on 18 June 2024)The Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022020),Further details can be found at http://xt.hnkjt.gov.cn/data/pingtai/(accessed on 18 June 2024)Natural Science Foundation of Henan Province Youth Science Fund Project(No.232300420422),you can visit https://kjt.henan.gov.cn/2022/09-02/2599082.html(accessed on 18 June 2024).
文摘In response to the challenges of generating Attribute-Based Access Control(ABAC)policies,this paper proposes a deep learning-based method to automatically generate ABAC policies from natural language documents.This method is aimed at organizations such as companies and schools that are transitioning from traditional access control models to the ABAC model.The manual retrieval and analysis involved in this transition are inefficient,prone to errors,and costly.Most organizations have high-level specifications defined for security policies that include a set of access control policies,which often exist in the form of natural language documents.Utilizing this rich source of information,our method effectively identifies and extracts the necessary attributes and rules for access control from natural language documents,thereby constructing and optimizing access control policies.This work transforms the problem of policy automation generation into two tasks:extraction of access control statements andmining of access control attributes.First,the Chat General Language Model(ChatGLM)isemployed to extract access control-related statements from a wide range of natural language documents by constructing unique prompts and leveraging the model’s In-Context Learning to contextualize the statements.Then,the Iterated Dilated-Convolutions-Conditional Random Field(ID-CNN-CRF)model is used to annotate access control attributes within these extracted statements,including subject attributes,object attributes,and action attributes,thus reassembling new access control policies.Experimental results show that our method,compared to baseline methods,achieved the highest F1 score of 0.961,confirming the model’s effectiveness and accuracy.
文摘Declining cognitive abilities can be a concomitant of advanced age.As language is closely associated with cognitive abilities,changes in language abilities can be an important marker of changes in cognitive abilities.The current study is to review cognitive studies of language and aging by first identifying and exploring the major clusters and pivotal articles and then detecting emerging trends.Data of 3,266 articles on language and aging from 2013 to 2022 were collected from the Web of Science Core Collection database.Adopting Document Co-citation Analysis,Freeman’s betweenness centrality metric(Freeman,2002)and Kleinberg’s burst detection algorithm(Kleinberg,2002),we explored major clusters,pivotal articles and emerging trends in this field.Cognition appears to be the most remarkable cluster.Bilingualism,speech production,listening effort,and reading comprehension are other major active clusters in a certain period.The most recent active cluster concerns the studies of Alzheimer’s disease.Articles serving as pivotal points concentrate on cognitive studies of the Framework for Understanding Effortful Listening(FUEL),the new Ease of Language Understanding model(EUL)and a hierarchical multi-representational generative framework of language comprehension.The progress in statistical methods,the relationship between language and cognitive impairment and the relationship between language abilities and cognition are the emerging trends.These emerging trends will provide some insights into how cognitive abilities influence language abilities in aging.
基金This work is part of the research projects LaTe4PoliticES(PID2022-138099OBI00)funded by MICIU/AEI/10.13039/501100011033the European Regional Development Fund(ERDF)-A Way of Making Europe and LT-SWM(TED2021-131167B-I00)funded by MICIU/AEI/10.13039/501100011033the European Union NextGenerationEU/PRTR.Mr.Ronghao Pan is supported by the Programa Investigo grant,funded by the Region of Murcia,the Spanish Ministry of Labour and Social Economy and the European Union-NextGenerationEU under the“Plan de Recuperación,Transformación y Resiliencia(PRTR).”。
文摘Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.
文摘Modern technological advancements have made social media an essential component of daily life.Social media allow individuals to share thoughts,emotions,and ideas.Sentiment analysis plays the function of evaluating whether the sentiment of the text is positive,negative,neutral,or any other personal emotion to understand the sentiment context of the text.Sentiment analysis is essential in business and society because it impacts strategic decision-making.Sentiment analysis involves challenges due to lexical variation,an unlabeled dataset,and text distance correlations.The execution time increases due to the sequential processing of the sequence models.However,the calculation times for the Transformer models are reduced because of the parallel processing.This study uses a hybrid deep learning strategy to combine the strengths of the Transformer and Sequence models while ignoring their limitations.In particular,the proposed model integrates the Decoding-enhanced with Bidirectional Encoder Representations from Transformers(BERT)attention(DeBERTa)and the Gated Recurrent Unit(GRU)for sentiment analysis.Using the Decoding-enhanced BERT technique,the words are mapped into a compact,semantic word embedding space,and the Gated Recurrent Unit model can capture the distance contextual semantics correctly.The proposed hybrid model achieves F1-scores of 97%on the Twitter Large Language Model(LLM)dataset,which is much higher than the performance of new techniques.
基金supported by the National Natural Science Foundation of China(Grant No.81974355 and No.82172524).
文摘Objective This study aimed to evaluate and compare the effectiveness of knowledge base-optimized and unoptimized large language models(LLMs)in the field of orthopedics to explore optimization strategies for the application of LLMs in specific fields.Methods This research constructed a specialized knowledge base using clinical guidelines from the American Academy of Orthopaedic Surgeons(AAOS)and authoritative orthopedic publications.A total of 30 orthopedic-related questions covering aspects such as anatomical knowledge,disease diagnosis,fracture classification,treatment options,and surgical techniques were input into both the knowledge base-optimized and unoptimized versions of the GPT-4,ChatGLM,and Spark LLM,with their generated responses recorded.The overall quality,accuracy,and comprehensiveness of these responses were evaluated by 3 experienced orthopedic surgeons.Results Compared with their unoptimized LLMs,the optimized version of GPT-4 showed improvements of 15.3%in overall quality,12.5%in accuracy,and 12.8%in comprehensiveness;ChatGLM showed improvements of 24.8%,16.1%,and 19.6%,respectively;and Spark LLM showed improvements of 6.5%,14.5%,and 24.7%,respectively.Conclusion The optimization of knowledge bases significantly enhances the quality,accuracy,and comprehensiveness of the responses provided by the 3 models in the orthopedic field.Therefore,knowledge base optimization is an effective method for improving the performance of LLMs in specific fields.
