Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles.While artificial intelligence(AI)offers promise,its typical need for vast datasets to learn from hinde...Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles.While artificial intelligence(AI)offers promise,its typical need for vast datasets to learn from hinders its use in these information-scarce frontiers.We introduce learning at criticality(LaC),a reinforcement learning scheme that tunes large language models(LLMs)to a sharp learning transition,addressing this information scarcity.At this transition,LLMs achieve peak generalization from minimal data,exemplified by 7-digit base-7 addition-a test of nontrivial arithmetic reasoning.To elucidate this peak,we analyze a minimal concept-network model designed to capture the essence of how LLMs might link tokens.Trained on a single exemplar,this model also undergoes a sharp learning transition.This transition exhibits hallmarks of a second-order phase transition,notably power-law distributed solution path lengths.At this critical point,the system maximizes a“critical thinking pattern”crucial for generalization,enabled by the underlying scale-free exploration.This suggests LLMs reach peak performance by operating at criticality,where such explorative dynamics enable the extraction of underlying operational rules.We demonstrate LaC in quantum field theory:an 8B-parameter LLM,tuned to its critical point by LaC using a few exemplars of symbolic Matsubara sums,solves unseen,higher-order problems,significantly outperforming far larger models.LaC thus leverages critical phenomena,a physical principle,to empower AI for complex,data-sparse challenges in fundamental physics.展开更多
We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of t...We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of these models and their ability to perform the task of abstractive text summarization in the healthcare field.The research hypothesis was that large language models could perform high-quality abstractive text summarization on German technical healthcare texts,even if the model is not specifically trained in that language.Through experiments,the research questions explore the performance of transformer language models in dealing with complex syntax constructs,the difference in performance between models trained in English and German,and the impact of translating the source text to English before conducting the summarization.We conducted an evaluation of four PLMs(GPT-3,a translation-based approach also utilizing GPT-3,a German language Model,and a domain-specific bio-medical model approach).The evaluation considered the informativeness using 3 types of metrics based on Recall-Oriented Understudy for Gisting Evaluation(ROUGE)and the quality of results which is manually evaluated considering 5 aspects.The results show that text summarization models could be used in the German healthcare domain and that domain-independent language models achieved the best results.The study proves that text summarization models can simplify the search for pre-existing German knowledge in various domains.展开更多
BACKGROUND Gastrointestinal diseases have complex etiologies and clinical presentations.An accurate diagnosis requires physicians to integrate diverse information,including medical history,laboratory test results,and ...BACKGROUND Gastrointestinal diseases have complex etiologies and clinical presentations.An accurate diagnosis requires physicians to integrate diverse information,including medical history,laboratory test results,and imaging findings.Existing artificial intelligence-assisted diagnostic tools are limited to single-modality information,resulting in recommendations that are often incomplete and may be associated with clinical or legal risks.AIM To develop and evaluate a collaborative multimodal large language model(LLM)framework for clinical decision-making in digestive diseases.METHODS In this observational study,DeepGut,a multimodal LLM collaborative diagnostic framework,was developed to integrate four distinct large models into a four-tiered structure.The framework sequentially accomplishes multimodal infor-mation extraction,logical“chain”construction,diagnostic and treatment suggestion generation,and risk analysis.The model was evaluated using objective metrics,which assess the reliability and comprehensiveness of model-generated results,and subjective expert opinions,which examine the effectiveness of the framework in assisting physicians.RESULTS The diagnostic and treatment recommendations generated by the DeepGut framework achieved exceptional performance,with a diagnostic accuracy of 97.8%,diagnostic completeness of 93.9%,treatment plan accuracy of 95.2%,and treatment plan completeness of 98.0%,significantly surpassing the capabilities of single-modal LLM-based diagnostic tools.Experts evaluating the framework commended the completeness,relevance,and logical coherence of its outputs.However,the collaborative multimodal LLM approach resulted in increased input and output token counts,leading to higher computational costs and extended diagnostic times.CONCLUSION The framework achieves successful integration of multimodal diagnostic data,demonstrating enhanced performance enabled by multimodal LLM collaboration,which opens new horizons for the clinical application of artificial intelligence-assisted technology.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
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
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
Peptide-based therapeutics hold great promise for the treatment of various diseases;however,their clinical application is often hindered by toxicity challenges.The accurate prediction of peptide toxicity is crucial fo...Peptide-based therapeutics hold great promise for the treatment of various diseases;however,their clinical application is often hindered by toxicity challenges.The accurate prediction of peptide toxicity is crucial for designing safe peptide-based therapeutics.While traditional experimental approaches are time-consuming and expensive,computational methods have emerged as viable alternatives,including similarity-based and machine learning(ML)-/deep learning(DL)-based methods.However,existing methods often struggle with robustness and generalizability.To address these challenges,we propose HyPepTox-Fuse,a novel framework that fuses protein language model(PLM)-based embeddings with conventional descriptors.HyPepTox-Fuse integrates ensemble PLM-based embeddings to achieve richer peptide representations by leveraging a cross-modal multi-head attention mechanism and Transformer architecture.A robust feature ranking and selection pipeline further refines conventional descriptors,thus enhancing prediction performance.Our framework outperforms state-of-the-art methods in cross-validation and independent evaluations,offering a scalable and reliable tool for peptide toxicity prediction.Moreover,we conducted a case study to validate the robustness and generalizability of HyPepTox-Fuse,highlighting its effectiveness in enhancing model performance.Furthermore,the HyPepTox-Fuse server is freely accessible at https://balalab-skku.org/HyPepTox-Fuse/and the source code is publicly available at https://github.com/cbbl-skku-org/HyPepTox-Fuse/.The study thus presents an intuitive platform for predicting peptide toxicity and supports reproducibility through openly available datasets.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
Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Class...Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Classifier(GPT2-ICC),which effectively distinguishing ion channels from a test set containing approximately 239 times more non-ion-channel proteins.GPT2-ICC integrates representation learning with a large language model(LLM)-based classifier,enabling highly accurate identification of potential ion channels.Several potential ion channels were predicated from the unannotated human proteome,further demonstrating GPT2-ICC’s generalization ability.This study marks a significant advancement in artificial-intelligence-driven ion channel research,highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data.Moreover,it provides a valuable computational tool for uncovering previously uncharacterized ion channels.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
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
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
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
The automatic diagnosis of depression plays a crucial role in preventing the deterioration of depression symptoms.The interview-based method is the most wildly adopted technique in depression diagnosis.However,the siz...The automatic diagnosis of depression plays a crucial role in preventing the deterioration of depression symptoms.The interview-based method is the most wildly adopted technique in depression diagnosis.However,the size of the collected conversation data is limited,and the sample distributions from different participants usually differ drastically.These factors present a great challenge in building a decent deep learning model for automatic depression diagnosis.Recently,large language models have demonstrated impressive capabilities and achieved human-level performance in various tasks under zero-shot and few-shot scenarios.This sheds new light on the development of AI solutions for domainspecific tasks with limited data.In this paper,we propose a two-stage approach that exploits the current most capable and cost-effective language model,ChatGPT,to make a depression diagnosis on interview-based data.Specifically,in the first stage,we use ChatGPT to summarize the raw dialogue sample,thereby facilitating the extraction of depression-related information.In the second stage,we use ChatGPT to classify the summarised data to predict the depressed state of the sample.Our method can achieve approximately 76%accuracy with a text-only modality on the DAIC-WOZ dataset.In addition,our method outperforms the performance of the state-of-the-art model by 6.2%in the D4 dataset.Our work highlights the potential of using large language models for diagnosis-based depression diagnosis.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
AIM:To investigate the capabilities of large language models(LLM)for providing information and diagnoses in the field of neuro-ophthalmology by comparing the performances of ChatGPT-3.5 and-4.0,Bard,and Bing.METHODS:E...AIM:To investigate the capabilities of large language models(LLM)for providing information and diagnoses in the field of neuro-ophthalmology by comparing the performances of ChatGPT-3.5 and-4.0,Bard,and Bing.METHODS:Each chatbot was evaluated for four criteria,namely diagnostic success rate for the described case,answer quality,response speed,and critical keywords for diagnosis.The selected topics included optic neuritis,nonarteritic anterior ischemic optic neuropathy,and Leber hereditary optic neuropathy.RESULTS:In terms of diagnostic success rate for the described cases,Bard was unable to provide a diagnosis.The success rates for the described cases increased in the order of Bing,ChatGPT-3.5,and ChatGPT-4.0.Further,ChatGPT-4.0 and-3.5 provided the most satisfactory answer quality for judgment by neuro-ophthalmologists,with their sets of answers resembling the sample set most.Bard was only able to provide ten differential diagnoses in three trials.Bing scored the lowest for the satisfactory standard.A Mann-Whitney test indicated that Bard was significantly faster than ChatGPT-4.0(Z=-3.576,P=0.000),ChatGPT-3.5(Z=-3.576,P=0.000)and Bing(Z=-2.517,P=0.011).ChatGPT-3.5 and-4.0 far exceeded the other two interfaces at providing diagnoses and were thus used to find the critical keywords for diagnosis.CONCLUSION:ChatGPT-3.5 and-4.0 are better than Bard and Bing in terms of answer success rate,answer quality,and critical keywords for diagnosis in ophthalmology.This study has broad implications for the field of ophthalmology,providing further evidence that artificial intelligence LLM can aid clinical decision-making through free-text explanations.展开更多
Short Message Service(SMS)is a widely used and cost-effective communication medium that has unfortunately become a frequent target for unsolicited messages-commonly known as SMS spam.With the rapid adoption of smartph...Short Message Service(SMS)is a widely used and cost-effective communication medium that has unfortunately become a frequent target for unsolicited messages-commonly known as SMS spam.With the rapid adoption of smartphones and increased Internet connectivity,SMS spam has emerged as a prevalent threat.Spammers have recognized the critical role SMS plays in today’s modern communication,making it a prime target for abuse.As cybersecurity threats continue to evolve,the volume of SMS spam has increased substantially in recent years.Moreover,the unstructured format of SMS data creates significant challenges for SMS spam detection,making it more difficult to successfully combat spam attacks.In this paper,we present an optimized and fine-tuned transformer-based Language Model to address the problem of SMS spam detection.We use a benchmark SMS spam dataset to analyze this spam detection model.Additionally,we utilize pre-processing techniques to obtain clean and noise-free data and address class imbalance problem by leveraging text augmentation techniques.The overall experiment showed that our optimized fine-tuned BERT(Bidirectional Encoder Representations from Transformers)variant model RoBERTa obtained high accuracy with 99.84%.To further enhance model transparency,we incorporate Explainable Artificial Intelligence(XAI)techniques that compute positive and negative coefficient scores,offering insight into the model’s decision-making process.Additionally,we evaluate the performance of traditional machine learning models as a baseline for comparison.This comprehensive analysis demonstrates the significant impact language models can have on addressing complex text-based challenges within the cybersecurity landscape.展开更多
The application of generative artificial intelligence(AI)is bringing about notable changes in anime creation.This paper surveys recent advancements and applications of diffusion and language models in anime generation...The application of generative artificial intelligence(AI)is bringing about notable changes in anime creation.This paper surveys recent advancements and applications of diffusion and language models in anime generation,focusing on their demonstrated potential to enhance production efficiency through automation and personalization.Despite these benefits,it is crucial to acknowledge the substantial initial computational investments required for training and deploying these models.We conduct an in-depth survey of cutting-edge generative AI technologies,encompassing models such as Stable Diffusion and GPT,and appraise pivotal large-scale datasets alongside quantifiable evaluation metrics.Review of the surveyed literature indicates the achievement of considerable maturity in the capacity of AI models to synthesize high-quality,aesthetically compelling anime visual images from textual prompts,alongside discernible progress in the generation of coherent narratives.However,achieving perfect long-form consistency,mitigating artifacts like flickering in video sequences,and enabling fine-grained artistic control remain critical ongoing challenges.Building upon these advancements,research efforts have increasingly pivoted towards the synthesis of higher-dimensional content,such as video and three-dimensional assets,with recent studies demonstrating significant progress in this burgeoning field.Nevertheless,formidable challenges endure amidst these advancements.Foremost among these are the substantial computational exigencies requisite for training and deploying these sophisticated models,particularly pronounced in the realm of high-dimensional generation such as video synthesis.Additional persistent hurdles include maintaining spatial-temporal consistency across complex scenes and mitigating ethical considerations surrounding bias and the preservation of human creative autonomy.This research underscores the transformative potential and inherent complexities of AI-driven synergy within the creative industries.We posit that future research should be dedicated to the synergistic fusion of diffusion and autoregressive models,the integration of multimodal inputs,and the balanced consideration of ethical implications,particularly regarding bias and the preservation of human creative autonomy,thereby establishing a robust foundation for the advancement of anime creation and the broader landscape of AI-driven content generation.展开更多
基金supported by the National Key Research and Development Program of China(Grant No.2024YFA1408604 for K.C.and X.C.)the National Natural Science Foundation of China(Grant Nos.12047503,12447103 for K.C.and X.C.,12325501 for P.Z.,and 12275263 for Y.D.and S.H.)+1 种基金the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0301900 for Y.D.and S.H.)the Natural Science Foundation of Fujian Province of China(Grant No.2023J02032 for Y.D.and S.H.)。
文摘Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles.While artificial intelligence(AI)offers promise,its typical need for vast datasets to learn from hinders its use in these information-scarce frontiers.We introduce learning at criticality(LaC),a reinforcement learning scheme that tunes large language models(LLMs)to a sharp learning transition,addressing this information scarcity.At this transition,LLMs achieve peak generalization from minimal data,exemplified by 7-digit base-7 addition-a test of nontrivial arithmetic reasoning.To elucidate this peak,we analyze a minimal concept-network model designed to capture the essence of how LLMs might link tokens.Trained on a single exemplar,this model also undergoes a sharp learning transition.This transition exhibits hallmarks of a second-order phase transition,notably power-law distributed solution path lengths.At this critical point,the system maximizes a“critical thinking pattern”crucial for generalization,enabled by the underlying scale-free exploration.This suggests LLMs reach peak performance by operating at criticality,where such explorative dynamics enable the extraction of underlying operational rules.We demonstrate LaC in quantum field theory:an 8B-parameter LLM,tuned to its critical point by LaC using a few exemplars of symbolic Matsubara sums,solves unseen,higher-order problems,significantly outperforming far larger models.LaC thus leverages critical phenomena,a physical principle,to empower AI for complex,data-sparse challenges in fundamental physics.
文摘We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of these models and their ability to perform the task of abstractive text summarization in the healthcare field.The research hypothesis was that large language models could perform high-quality abstractive text summarization on German technical healthcare texts,even if the model is not specifically trained in that language.Through experiments,the research questions explore the performance of transformer language models in dealing with complex syntax constructs,the difference in performance between models trained in English and German,and the impact of translating the source text to English before conducting the summarization.We conducted an evaluation of four PLMs(GPT-3,a translation-based approach also utilizing GPT-3,a German language Model,and a domain-specific bio-medical model approach).The evaluation considered the informativeness using 3 types of metrics based on Recall-Oriented Understudy for Gisting Evaluation(ROUGE)and the quality of results which is manually evaluated considering 5 aspects.The results show that text summarization models could be used in the German healthcare domain and that domain-independent language models achieved the best results.The study proves that text summarization models can simplify the search for pre-existing German knowledge in various domains.
基金Supported by China Health Promotion Foundation Young Doctors’Research Foundation for Inflammatory Bowel DiseaseTaishan Scholars Program of Shandong Province,China,NO.tsqn202306343National Natural Science Foundation of China,No.82270580,No.82070552,No.82270578,and No.82300599.
文摘BACKGROUND Gastrointestinal diseases have complex etiologies and clinical presentations.An accurate diagnosis requires physicians to integrate diverse information,including medical history,laboratory test results,and imaging findings.Existing artificial intelligence-assisted diagnostic tools are limited to single-modality information,resulting in recommendations that are often incomplete and may be associated with clinical or legal risks.AIM To develop and evaluate a collaborative multimodal large language model(LLM)framework for clinical decision-making in digestive diseases.METHODS In this observational study,DeepGut,a multimodal LLM collaborative diagnostic framework,was developed to integrate four distinct large models into a four-tiered structure.The framework sequentially accomplishes multimodal infor-mation extraction,logical“chain”construction,diagnostic and treatment suggestion generation,and risk analysis.The model was evaluated using objective metrics,which assess the reliability and comprehensiveness of model-generated results,and subjective expert opinions,which examine the effectiveness of the framework in assisting physicians.RESULTS The diagnostic and treatment recommendations generated by the DeepGut framework achieved exceptional performance,with a diagnostic accuracy of 97.8%,diagnostic completeness of 93.9%,treatment plan accuracy of 95.2%,and treatment plan completeness of 98.0%,significantly surpassing the capabilities of single-modal LLM-based diagnostic tools.Experts evaluating the framework commended the completeness,relevance,and logical coherence of its outputs.However,the collaborative multimodal LLM approach resulted in increased input and output token counts,leading to higher computational costs and extended diagnostic times.CONCLUSION The framework achieves successful integration of multimodal diagnostic data,demonstrating enhanced performance enabled by multimodal LLM collaboration,which opens new horizons for the clinical application of artificial intelligence-assisted technology.
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.
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 National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT,Republic of Korea(Grant No.:RS-2024-00344752)supported by the Department of Integrative Biotechnology,Sungkyunkwan University(SKKU)and the BK21 FOUR Project,Republic of Korea.
文摘Peptide-based therapeutics hold great promise for the treatment of various diseases;however,their clinical application is often hindered by toxicity challenges.The accurate prediction of peptide toxicity is crucial for designing safe peptide-based therapeutics.While traditional experimental approaches are time-consuming and expensive,computational methods have emerged as viable alternatives,including similarity-based and machine learning(ML)-/deep learning(DL)-based methods.However,existing methods often struggle with robustness and generalizability.To address these challenges,we propose HyPepTox-Fuse,a novel framework that fuses protein language model(PLM)-based embeddings with conventional descriptors.HyPepTox-Fuse integrates ensemble PLM-based embeddings to achieve richer peptide representations by leveraging a cross-modal multi-head attention mechanism and Transformer architecture.A robust feature ranking and selection pipeline further refines conventional descriptors,thus enhancing prediction performance.Our framework outperforms state-of-the-art methods in cross-validation and independent evaluations,offering a scalable and reliable tool for peptide toxicity prediction.Moreover,we conducted a case study to validate the robustness and generalizability of HyPepTox-Fuse,highlighting its effectiveness in enhancing model performance.Furthermore,the HyPepTox-Fuse server is freely accessible at https://balalab-skku.org/HyPepTox-Fuse/and the source code is publicly available at https://github.com/cbbl-skku-org/HyPepTox-Fuse/.The study thus presents an intuitive platform for predicting peptide toxicity and supports reproducibility through openly available datasets.
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funded by grants from the National Key Research and Development Program of China(Grant Nos.:2022YFE0205600 and 2022YFC3400504)the National Natural Science Foundation of China(Grant Nos.:82373792 and 82273857)the Fundamental Research Funds for the Central Universities,China,and the East China Normal University Medicine and Health Joint Fund,China(Grant No.:2022JKXYD07001).
文摘Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Classifier(GPT2-ICC),which effectively distinguishing ion channels from a test set containing approximately 239 times more non-ion-channel proteins.GPT2-ICC integrates representation learning with a large language model(LLM)-based classifier,enabling highly accurate identification of potential ion channels.Several potential ion channels were predicated from the unannotated human proteome,further demonstrating GPT2-ICC’s generalization ability.This study marks a significant advancement in artificial-intelligence-driven ion channel research,highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data.Moreover,it provides a valuable computational tool for uncovering previously uncharacterized ion channels.
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 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.
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.
基金supported by the Science and Technology Innovation 2030 Project of China(2021ZD0202600).
文摘The automatic diagnosis of depression plays a crucial role in preventing the deterioration of depression symptoms.The interview-based method is the most wildly adopted technique in depression diagnosis.However,the size of the collected conversation data is limited,and the sample distributions from different participants usually differ drastically.These factors present a great challenge in building a decent deep learning model for automatic depression diagnosis.Recently,large language models have demonstrated impressive capabilities and achieved human-level performance in various tasks under zero-shot and few-shot scenarios.This sheds new light on the development of AI solutions for domainspecific tasks with limited data.In this paper,we propose a two-stage approach that exploits the current most capable and cost-effective language model,ChatGPT,to make a depression diagnosis on interview-based data.Specifically,in the first stage,we use ChatGPT to summarize the raw dialogue sample,thereby facilitating the extraction of depression-related information.In the second stage,we use ChatGPT to classify the summarised data to predict the depressed state of the sample.Our method can achieve approximately 76%accuracy with a text-only modality on the DAIC-WOZ dataset.In addition,our method outperforms the performance of the state-of-the-art model by 6.2%in the D4 dataset.Our work highlights the potential of using large language models for diagnosis-based depression diagnosis.
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AIM:To investigate the capabilities of large language models(LLM)for providing information and diagnoses in the field of neuro-ophthalmology by comparing the performances of ChatGPT-3.5 and-4.0,Bard,and Bing.METHODS:Each chatbot was evaluated for four criteria,namely diagnostic success rate for the described case,answer quality,response speed,and critical keywords for diagnosis.The selected topics included optic neuritis,nonarteritic anterior ischemic optic neuropathy,and Leber hereditary optic neuropathy.RESULTS:In terms of diagnostic success rate for the described cases,Bard was unable to provide a diagnosis.The success rates for the described cases increased in the order of Bing,ChatGPT-3.5,and ChatGPT-4.0.Further,ChatGPT-4.0 and-3.5 provided the most satisfactory answer quality for judgment by neuro-ophthalmologists,with their sets of answers resembling the sample set most.Bard was only able to provide ten differential diagnoses in three trials.Bing scored the lowest for the satisfactory standard.A Mann-Whitney test indicated that Bard was significantly faster than ChatGPT-4.0(Z=-3.576,P=0.000),ChatGPT-3.5(Z=-3.576,P=0.000)and Bing(Z=-2.517,P=0.011).ChatGPT-3.5 and-4.0 far exceeded the other two interfaces at providing diagnoses and were thus used to find the critical keywords for diagnosis.CONCLUSION:ChatGPT-3.5 and-4.0 are better than Bard and Bing in terms of answer success rate,answer quality,and critical keywords for diagnosis in ophthalmology.This study has broad implications for the field of ophthalmology,providing further evidence that artificial intelligence LLM can aid clinical decision-making through free-text explanations.
文摘Short Message Service(SMS)is a widely used and cost-effective communication medium that has unfortunately become a frequent target for unsolicited messages-commonly known as SMS spam.With the rapid adoption of smartphones and increased Internet connectivity,SMS spam has emerged as a prevalent threat.Spammers have recognized the critical role SMS plays in today’s modern communication,making it a prime target for abuse.As cybersecurity threats continue to evolve,the volume of SMS spam has increased substantially in recent years.Moreover,the unstructured format of SMS data creates significant challenges for SMS spam detection,making it more difficult to successfully combat spam attacks.In this paper,we present an optimized and fine-tuned transformer-based Language Model to address the problem of SMS spam detection.We use a benchmark SMS spam dataset to analyze this spam detection model.Additionally,we utilize pre-processing techniques to obtain clean and noise-free data and address class imbalance problem by leveraging text augmentation techniques.The overall experiment showed that our optimized fine-tuned BERT(Bidirectional Encoder Representations from Transformers)variant model RoBERTa obtained high accuracy with 99.84%.To further enhance model transparency,we incorporate Explainable Artificial Intelligence(XAI)techniques that compute positive and negative coefficient scores,offering insight into the model’s decision-making process.Additionally,we evaluate the performance of traditional machine learning models as a baseline for comparison.This comprehensive analysis demonstrates the significant impact language models can have on addressing complex text-based challenges within the cybersecurity landscape.
基金supported by the National Natural Science Foundation of China(Grant No.62202210).
文摘The application of generative artificial intelligence(AI)is bringing about notable changes in anime creation.This paper surveys recent advancements and applications of diffusion and language models in anime generation,focusing on their demonstrated potential to enhance production efficiency through automation and personalization.Despite these benefits,it is crucial to acknowledge the substantial initial computational investments required for training and deploying these models.We conduct an in-depth survey of cutting-edge generative AI technologies,encompassing models such as Stable Diffusion and GPT,and appraise pivotal large-scale datasets alongside quantifiable evaluation metrics.Review of the surveyed literature indicates the achievement of considerable maturity in the capacity of AI models to synthesize high-quality,aesthetically compelling anime visual images from textual prompts,alongside discernible progress in the generation of coherent narratives.However,achieving perfect long-form consistency,mitigating artifacts like flickering in video sequences,and enabling fine-grained artistic control remain critical ongoing challenges.Building upon these advancements,research efforts have increasingly pivoted towards the synthesis of higher-dimensional content,such as video and three-dimensional assets,with recent studies demonstrating significant progress in this burgeoning field.Nevertheless,formidable challenges endure amidst these advancements.Foremost among these are the substantial computational exigencies requisite for training and deploying these sophisticated models,particularly pronounced in the realm of high-dimensional generation such as video synthesis.Additional persistent hurdles include maintaining spatial-temporal consistency across complex scenes and mitigating ethical considerations surrounding bias and the preservation of human creative autonomy.This research underscores the transformative potential and inherent complexities of AI-driven synergy within the creative industries.We posit that future research should be dedicated to the synergistic fusion of diffusion and autoregressive models,the integration of multimodal inputs,and the balanced consideration of ethical implications,particularly regarding bias and the preservation of human creative autonomy,thereby establishing a robust foundation for the advancement of anime creation and the broader landscape of AI-driven content generation.
