Dear Editor,This letter introduces the counterfactual-guided implicit correspondence prompting(CICP)framework,designed for visible-infrared person re-identification(VI-ReID)within Industry 5.0 intelligent control syst...Dear Editor,This letter introduces the counterfactual-guided implicit correspondence prompting(CICP)framework,designed for visible-infrared person re-identification(VI-ReID)within Industry 5.0 intelligent control systems.CICP advances recognition accuracy in complex industrial environments through its innovative approach to handling modality-specific features and their implicit relationships.展开更多
Chinese abbreviations improve communicative efficiency by extracting key components from longer expressions.They are widely used in both daily communication and professional domains.However,existing abbreviation gener...Chinese abbreviations improve communicative efficiency by extracting key components from longer expressions.They are widely used in both daily communication and professional domains.However,existing abbreviation generation methods still face two major challenges.First,sequence-labeling-based approaches often neglect contextual meaning by making binary decisions at the character level,leading to abbreviations that fail to capture semantic completeness.Second,generation-basedmethods rely heavily on a single decoding process,which frequently produces correct abbreviations but ranks them lower due to inadequate semantic evaluation.To address these limitations,we propose a novel two-stage frameworkwithGeneration–Iterative Optimization forAbbreviation(GIOA).In the first stage,we design aChain-of-Thought prompting strategy and incorporate definitional and situational contexts to generate multiple abbreviation candidates.In the second stage,we introduce a Semantic Preservation Dynamic Adjustment mechanism that alternates between character-level importance estimation and semantic restoration to optimize candidate ranking.Experiments on two public benchmark datasets show that our method outperforms existing state-of-the-art approaches,achieving Hit@1 improvements of 15.15%and 13.01%,respectively,while maintaining consistent results in Hit@3.展开更多
Automatic and accurate medical image segmentation remains a fundamental task in computer-aided diagnosis and treatment planning.Recent advances in foundation models,such as the medical-focused Segment AnythingModel(Me...Automatic and accurate medical image segmentation remains a fundamental task in computer-aided diagnosis and treatment planning.Recent advances in foundation models,such as the medical-focused Segment AnythingModel(MedSAM),have demonstrated strong performance but face challenges inmanymedical applications due to anatomical complexity and a limited domain-specific prompt.Thiswork introduces amethodology that enhances segmentation robustness and precision by automatically generating multiple informative point prompts,rather than relying on single inputs.The proposed approach randomly samples sets of spatially distributed point prompts based on image features,enabling MedSAM to better capture fine-grained anatomical structures and boundaries.During inference,probability maps are aggregated to reduce local misclassifications without additional model training.Extensive experiments on various computed tomography(CT)and magnetic resonance imaging(MRI)datasets demonstrate improvements in Dice Similarity Coefficient(DSC)and Normalized Surface Dice(NSD)metrics compared to baseline SAM and Scribble Prompt models.A semi-automatic point sampling version based on the ground truth segmentations yielded enhanced results,achieving up to 92.1%DSC and 86.6%NSD,with significant gains in delineating complex organs such as the pancreas,colon,kidney,and brain tumours.The main novelty of our method consists of effectively combining the results of multiple point prompts into the medical segmentation pipeline so that single-point prompt methods are outperformed.Overall,the proposed model offers a straightforward yet effective approach to improve medical image segmentation performance while maintaining computational efficiency.展开更多
Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step...Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.展开更多
Information extraction(IE)aims to automatically identify and extract information about specific interests from raw texts.Despite the abundance of solutions based on fine-tuning pretrained language models,IE in the con...Information extraction(IE)aims to automatically identify and extract information about specific interests from raw texts.Despite the abundance of solutions based on fine-tuning pretrained language models,IE in the context of fewshot and zero-shot scenarios remains highly challenging due to the scarcity of training data.Large language models(LLMs),on the other hand,can generalize well to unseen tasks with few-shot demonstrations or even zero-shot instructions and have demonstrated impressive ability for a wide range of natural language understanding or generation tasks.Nevertheless,it is unclear,whether such effectiveness can be replicated in the task of IE,where the target tasks involve specialized schema and quite abstractive entity or relation concepts.In this paper,we first examine the validity of LLMs in executing IE tasks with an established prompting strategy and further propose multiple types of augmented prompting methods,including the structured fundamental prompt(SFP),the structured interactive reasoning prompt(SIRP),and the voting-enabled structured interactive reasoning prompt(VESIRP).The experimental results demonstrate that while directly promotes inferior performance,the proposed augmented prompt methods significantly improve the extraction accuracy,achieving comparable or even better performance(e.g.,zero-shot FewNERD,FewNERD-INTRA)than state-of-theart methods that require large-scale training samples.This study represents a systematic exploration of employing instruction-following LLM for the task of IE.It not only establishes a performance benchmark for this novel paradigm but,more importantly,validates a practical technical pathway through the proposed prompt enhancement method,offering a viable solution for efficient IE in low-resource settings.展开更多
With the further implementation of the knowledge innovation program (KIP), piloted by the Chinese Academy of Sciences (CAS), encouraging progress has been made in contributing to the development of the country's h...With the further implementation of the knowledge innovation program (KIP), piloted by the Chinese Academy of Sciences (CAS), encouraging progress has been made in contributing to the development of the country's high-tech industry, and forging S&T cooperation with local governments and industrial sectors. This was revealed at the Second CAS Conference on High-tech Industrialization April 25 - 29 in Shenzhen, Guangdong Province.展开更多
Accurate crop disease classification is essential for disease management to support food security.Deep learning has shown its high classification accuracy in image-based disease identification.However,the deep learnin...Accurate crop disease classification is essential for disease management to support food security.Deep learning has shown its high classification accuracy in image-based disease identification.However,the deep learning approach usually needs large amounts of data for training to achieve satisfactory performance,which hindering its application and scalability for different crops.Large language models(LLMs)have shown strong generation capability and zero-shot performance.While how to utilize the LLM technique for crop disease classification remains unclear.In this study,we developed a training-free framework named ChatLeafDisease(ChatLD)based on GPT-4o model with chain-of-thought(CoT)prompting for crop disease classification.The framework includes a disease description database to provide knowledge of crop diseases and a disease classification agent guided by CoT prompts to understand the patterns of leaves infected diseases and classify the disease.The original GPT-4o model,Gemini model,and Contrastive Language-Image Pre-training(CLIP)model were chosen as baselines.Results showed that the ChatLD framework achieved higher and more stable classification accuracy(88.9%)for six tomato diseases than the GPT-4o(45.9%),Gemini(56.1%),and CLIP(64.3%)models.We found that the scoring rules enabled the ChatLD framework to capture the typical differences across diseases.Ablation results showed that the CoT prompts integrated the scoring rules and important notes to enable the ChatLD to achieve high classification accuracy.Comparison between different description texts showed that condensed disease description improved the classification performance.The results showed that the ChatLD framework achieved high accuracy for the disease classes of new crops,highlighting its scalability across various crop diseases.The proposed framework provided a new LLM-based alternative for crop disease classification by only using the textual descriptions of disease without training process.展开更多
Semi-supervised sound event detection(SSED)tasks typically leverage a large amount of unlabeled and synthetic data to facilitate model generalization during training,reducing overfitting on a limited set of labeled da...Semi-supervised sound event detection(SSED)tasks typically leverage a large amount of unlabeled and synthetic data to facilitate model generalization during training,reducing overfitting on a limited set of labeled data.However,the generalization training process often encounters challenges from noisy interference introduced by pseudo-labels or domain knowledge gaps.To alleviate noisy interference in class distribution learning,we propose an efficient semi-supervised class distribution learning method through dynamic prompt tuning,named prompting class distribution optimization(PADO).Specifically,when modeling real labeled data,PADO dynamically incorporates independent learnable prompt tokens to explore prior knowledge about the true distribution.Then,the prior knowledge serves as prompt information,dynamically interacting with the posterior noisy-class distribution information.In this case,PADO achieves class distribution optimization while maintaining model generalization,leading to a significant improvement in the efficiency of class distribution learning.Compared with state-of-the-art methods on the SSED datasets from DCASE 2019,2020,and 2021 challenges,PADO achieves significant performance improvements.Furthermore,it is readily extendable to other benchmark models.展开更多
Automatic question tagging(AQT)represents a crucial task in community question answering(CQA)websites.Its pivotal role lies in substantially augmenting user experience through the optimization of question-answering ef...Automatic question tagging(AQT)represents a crucial task in community question answering(CQA)websites.Its pivotal role lies in substantially augmenting user experience through the optimization of question-answering efficiency.Existing question tagging models focus on the features of questions and tags,ignoring the external knowledge of the real world.Large language models can work as knowledge engines for incorporating real-world facts for different tasks.However,it is difficult for large language models to output tags in the database of CQA websites.To address this challenge,we propose a large language model enhanced question tagging method called LLMEQT to perform the question tagging task.In LLMEQT,a traditional question tagging method is first applied to pre-retrieve tags for questions.Then prompts are formulated for LLMs to comprehend the task and select more suitable tags from the candidate tags for questions.Results of our experiments on two real-world datasets demonstrate that LLMEQT significantly enhances the automatic question tagging performance for CQA,surpassing the performance of state-of-the-art methods.展开更多
Large language models(LLMs)show great potential in educational scenarios but face challenges like hallucination,knowledge gaps,and reasoning discontinuities.This study proposes a dynamic knowledge enhancement framewor...Large language models(LLMs)show great potential in educational scenarios but face challenges like hallucination,knowledge gaps,and reasoning discontinuities.This study proposes a dynamic knowledge enhancement framework.By integrating local knowledge graphs and stepwise prompting mechanisms,it improves LLMs’accuracy and interpretability in solving professional domain problems.The framework has two core modules:an LLM-driven knowledge graph construction system for incremental updates and a unified reasoning engine for generating enhanced prompts.Experiments on 680 educational questions show that the method boosts accuracy by 4.5%and 4.3%for multi-step reasoning and knowledge-dependent questions respectively,and increases reasoning step completeness from 68.2%to 83.7%.It also reduces hallucination problems.Key contributions include the followings:①validation of an effective framework synergizing knowledge graphs with retrieval mechanisms to enhance LLM reliability;②a stepwise prompting strategy enforcing explicit reasoning chain generation,addressing pedagogical requirements for process interpretability;③a lightweight deployment solution for educational systems such as adaptive learning platforms.展开更多
The springing up of large language models(LLMs)has shifted the community from single-task-orientated natural language processing(NLP)research to a holistic end-to-end multi-task learning paradigm.Along this line of re...The springing up of large language models(LLMs)has shifted the community from single-task-orientated natural language processing(NLP)research to a holistic end-to-end multi-task learning paradigm.Along this line of research endeavors in the area,LLM-based prompting methods have attracted much attention,partially due to the technological advantages brought by prompt engineering(PE)as well as the underlying NLP principles disclosed by various prompting methods.Traditional supervised learning usually requires training a model based on labeled data and then making predictions.In contrast,PE methods directly use the powerful capabilities of existing LLMs(e.g.,GPT-3 and GPT-4)via composing appropriate prompts,especially under few-shot or zero-shot scenarios.Facing the abundance of studies related to the prompting and the ever-evolving nature of this field,this article aims to 1)illustrate a novel perspective to review existing PE methods within the well-established communication theory framework,2)facilitate a better/deeper understanding of developing trends of existing PE methods used in three typical tasks,and 3)shed light on promising research directions for future PE methods.展开更多
Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that man...Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.展开更多
The energy correlations of prompt fission neutrons have not yet been considered in the related coincidence and multiplication measurement techniques.To measure and verify the energy correlations,an experiment was perf...The energy correlations of prompt fission neutrons have not yet been considered in the related coincidence and multiplication measurement techniques.To measure and verify the energy correlations,an experiment was performed with a total measurement duration of approximately 1200 h.In the experiment,eight CLYC detectors and sixteen EJ309 liquid scintillation detectors were utilized,and the fission moment was tagged with the measured fissionγ-rays.The relative ratios of the energy spectra of the neutrons correlated with different energy neutrons to the^(252)Cf fission neutron energy spectra were obtained.The present results may be helpful for studying fission physics and nuclear technology applications.展开更多
The outstanding growth in the applications of large language models(LLMs)demonstrates the significance of adaptive and efficient prompt engineering tactics.The existing methods may not be variable,vigorous and streaml...The outstanding growth in the applications of large language models(LLMs)demonstrates the significance of adaptive and efficient prompt engineering tactics.The existing methods may not be variable,vigorous and streamlined in different domains.The offered study introduces an immediate optimization outline,named PROMPTx-PE,that is going to yield a greater level of precision and strength when it comes to the assignments that are premised on LLM.The proposed systemfeatures a timely selection schemewhich is informed by reinforcement learning,a contextual layer and a dynamic weighting module which is regulated by Lyapunov-based stability guidelines.The PROMPTx-PE dynamically varies the exploration and exploitation of the prompt space,depending on real-time feedback and multi-objective reward development.Extensive testing on both benchmark(GLUE,SuperGLUE)and domain-specific data(Healthcare-QA and Industrial-NER)demonstrates a large best performance to be 89.4%and a strong robustness disconnect with under 3%computation expense.The results confirm the effectiveness,consistency,and scalability of PROMPTx-PE as a platform of adaptive prompt engineering based on recent uses of LLMs.展开更多
The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(L...The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(LLMs)such as GPT-4.Zero excels in natural language understanding tasks but can still struggle to distinguish between fact and fiction,particularly when applied in the wild.However,a key challenge of existing FND methods is that they only consider unimodal data(e.g.,images),while more detailed multimodal data(e.g.,user behaviour,temporal dynamics)is neglected,and the latter is crucial for full-context understanding.To overcome these limitations,we introduce M3-FND(Multimodal Misinformation Mitigation for False News Detection),a novel methodological framework that integrates LLMs with multimodal data sources to perform context-aware veracity assessments.Our method proposes a hybrid system that combines image-text alignment,user credibility profiling,and temporal pattern recognition,which is also strengthened through a natural feedback loop that provides real-time feedback for correcting downstream errors.We use contextual reinforcement learning to schedule prompt updating and update the classifier threshold based on the latest multimodal input,which enables the model to better adapt to changing misinformation attack strategies.M3-FND is tested on three diverse datasets,FakeNewsNet,Twitter15,andWeibo,which contain both text and visual socialmedia content.Experiments showthatM3-FND significantly outperforms conventional and LLMbased baselines in terms of accuracy,F1-score,and AUC on all benchmarks.Our results indicate the importance of employing multimodal cues and adaptive learning for effective and timely detection of fake news.展开更多
Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural ...Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural artifacts online.As an effective medium,posters serve to attract public attention and facilitate broader engagement with cultural artifacts.However,existing poster generation methods mainly rely on fixed templates and manual design,which limits their scalability and adaptability to the diverse visual and semantic features of the artifacts.Therefore,we propose CAPGen,an automated aesthetic Cultural Artifacts Poster Generation framework built on a Multimodal Large Language Model(MLLM)with integrated iterative optimization.During our research,we collaborated with designers to define principles of graphic design for cultural artifact posters,to guide the MLLM in generating layout parameters.Later,we generated these parameters into posters.Finally,we refined the posters using an MLLM integrated with a multi-round iterative optimization mechanism.Qualitative results show that CAPGen consistently outperforms baseline methods in both visual quality and aesthetic performance.Furthermore,ablation studies indicate that the prompt,iterative optimization mechanism,and design principles significantly enhance the effectiveness of poster generation.展开更多
While Large Language Models(LLMs)possess the capability to perform a wide range of tasks,security attacks known as prompt injection and jailbreaking remain critical challenges.Existing defense approaches addressing th...While Large Language Models(LLMs)possess the capability to perform a wide range of tasks,security attacks known as prompt injection and jailbreaking remain critical challenges.Existing defense approaches addressing this problem face challenges such as the over-refusal of prompts that contain harmful vocabulary but are semantically benign,and the limited accuracy improvement inmachine learning-based approaches due to the ease of distinguishing benign prompts in existing datasets.Therefore,we propose a multi-LLM agent framework aimed at achieving both the accurate rejection of harmful prompts and appropriate responses to benign prompts.Distinct from prior studies,the proposed method adopts In-Context Learning(ICL)during the learning phase,presenting a novel approach that obviates the need for computationally expensive parameter updates required by conventional fine-tuning.To demonstrate the proposed method’s capability for rapid and easy deployment,this study targets LLMs with insufficient alignment.In the experiments,macro-averaged binary classification metrics were used to comprehensively evaluate harmfulness detection.Experimental results using three LLMs demonstrated that the proposed method achieved performance that surpassed four baselines across all evaluation metrics for the target LLMs,evidencing significant effectiveness with an average improvement of 16.6 points in F1-score compared to the vanilla models.The significance of this study lies in the proposal of a novel approach based on ICL that does not require parameter updates.This framework offers high sustainability in practical deployment,as it allows for the adaptive enhancement of detection performance against continuously evolving attack methods solely through the accumulation of logs,without the necessity of retraining the LLM itself.By mitigating the trade-off between safety and utility,this research contributes to the implementation of robust LLMs.展开更多
基金supported in part by the National Natural Science Foundation of China(62406177)the Shandong Excellent Young Scientists Fund(Oversea)(2024HWYQ-027)+1 种基金the Natural Science Foundation of Shandong Province(ZR2023QF124)the Young Scholars Program of Shandong University。
文摘Dear Editor,This letter introduces the counterfactual-guided implicit correspondence prompting(CICP)framework,designed for visible-infrared person re-identification(VI-ReID)within Industry 5.0 intelligent control systems.CICP advances recognition accuracy in complex industrial environments through its innovative approach to handling modality-specific features and their implicit relationships.
基金supported by the National Key Research and Development Program of China(2020AAA0109300)the Shanghai Collaborative Innovation Center of data intelligence technology(No.0232-A1-8900-24-13).
文摘Chinese abbreviations improve communicative efficiency by extracting key components from longer expressions.They are widely used in both daily communication and professional domains.However,existing abbreviation generation methods still face two major challenges.First,sequence-labeling-based approaches often neglect contextual meaning by making binary decisions at the character level,leading to abbreviations that fail to capture semantic completeness.Second,generation-basedmethods rely heavily on a single decoding process,which frequently produces correct abbreviations but ranks them lower due to inadequate semantic evaluation.To address these limitations,we propose a novel two-stage frameworkwithGeneration–Iterative Optimization forAbbreviation(GIOA).In the first stage,we design aChain-of-Thought prompting strategy and incorporate definitional and situational contexts to generate multiple abbreviation candidates.In the second stage,we introduce a Semantic Preservation Dynamic Adjustment mechanism that alternates between character-level importance estimation and semantic restoration to optimize candidate ranking.Experiments on two public benchmark datasets show that our method outperforms existing state-of-the-art approaches,achieving Hit@1 improvements of 15.15%and 13.01%,respectively,while maintaining consistent results in Hit@3.
基金supported by the Autonomous Government of Andalusia(Spain)under project UMA20-FEDERJA-108also by the Ministry of Science and Innovation of Spain,grant number PID2022-136764OA-I00+1 种基金It includes funds fromthe European Regional Development Fund(ERDF),It is also partially supported by the Fundación Unicaja(PUNI-003_2023)the Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina-IBIMA Plataforma BIONAND(ATECH-25-02).
文摘Automatic and accurate medical image segmentation remains a fundamental task in computer-aided diagnosis and treatment planning.Recent advances in foundation models,such as the medical-focused Segment AnythingModel(MedSAM),have demonstrated strong performance but face challenges inmanymedical applications due to anatomical complexity and a limited domain-specific prompt.Thiswork introduces amethodology that enhances segmentation robustness and precision by automatically generating multiple informative point prompts,rather than relying on single inputs.The proposed approach randomly samples sets of spatially distributed point prompts based on image features,enabling MedSAM to better capture fine-grained anatomical structures and boundaries.During inference,probability maps are aggregated to reduce local misclassifications without additional model training.Extensive experiments on various computed tomography(CT)and magnetic resonance imaging(MRI)datasets demonstrate improvements in Dice Similarity Coefficient(DSC)and Normalized Surface Dice(NSD)metrics compared to baseline SAM and Scribble Prompt models.A semi-automatic point sampling version based on the ground truth segmentations yielded enhanced results,achieving up to 92.1%DSC and 86.6%NSD,with significant gains in delineating complex organs such as the pancreas,colon,kidney,and brain tumours.The main novelty of our method consists of effectively combining the results of multiple point prompts into the medical segmentation pipeline so that single-point prompt methods are outperformed.Overall,the proposed model offers a straightforward yet effective approach to improve medical image segmentation performance while maintaining computational efficiency.
基金National Natural Science Foundation of China(No.62176052)。
文摘Large language models(LLMs)have demonstrated remarkable generalization abilities across multiple tasks in natural language processing(NLP).For multi-step reasoning tasks,chain-of-thought(CoT)prompting facilitates step-by-step thinking,leading to improved performance.However,despite significant advancements in LLMs,current CoT prompting performs suboptimally on smaller-scale models that have fewer parameters.Additionally,the common paradigm of few-shot CoT prompting relies on a set of manual demonstrations,with performance contingent on the quality of these annotations and varying with task-specific requirements.To address these limitations,we propose a select-and-answer prompting method(SAP)to enhance language model performance on reasoning tasks without the need for manual demonstrations.This method comprises two primary steps:guiding the model to conduct preliminary analysis and generate several candidate answers based on the prompting;allowing the model to provide final answers derived from these candidate answers.The proposed prompting strategy is evaluated across two language models of varying sizes and six datasets.On ChatGLM-6B,SAP consistently outperforms few-shot CoT across all datasets.For GPT-3.5,SAP achieves comparable performance to few-shot CoT and outperforms zero-shot CoT in most cases.These experimental results indicate that SAP can significantly improve the accuracy of language models in reasoning tasks.
基金supported by the National Natural Science Foundation of China(62222212).
文摘Information extraction(IE)aims to automatically identify and extract information about specific interests from raw texts.Despite the abundance of solutions based on fine-tuning pretrained language models,IE in the context of fewshot and zero-shot scenarios remains highly challenging due to the scarcity of training data.Large language models(LLMs),on the other hand,can generalize well to unseen tasks with few-shot demonstrations or even zero-shot instructions and have demonstrated impressive ability for a wide range of natural language understanding or generation tasks.Nevertheless,it is unclear,whether such effectiveness can be replicated in the task of IE,where the target tasks involve specialized schema and quite abstractive entity or relation concepts.In this paper,we first examine the validity of LLMs in executing IE tasks with an established prompting strategy and further propose multiple types of augmented prompting methods,including the structured fundamental prompt(SFP),the structured interactive reasoning prompt(SIRP),and the voting-enabled structured interactive reasoning prompt(VESIRP).The experimental results demonstrate that while directly promotes inferior performance,the proposed augmented prompt methods significantly improve the extraction accuracy,achieving comparable or even better performance(e.g.,zero-shot FewNERD,FewNERD-INTRA)than state-of-theart methods that require large-scale training samples.This study represents a systematic exploration of employing instruction-following LLM for the task of IE.It not only establishes a performance benchmark for this novel paradigm but,more importantly,validates a practical technical pathway through the proposed prompt enhancement method,offering a viable solution for efficient IE in low-resource settings.
文摘With the further implementation of the knowledge innovation program (KIP), piloted by the Chinese Academy of Sciences (CAS), encouraging progress has been made in contributing to the development of the country's high-tech industry, and forging S&T cooperation with local governments and industrial sectors. This was revealed at the Second CAS Conference on High-tech Industrialization April 25 - 29 in Shenzhen, Guangdong Province.
基金This work was supported by Key R&D Program of Zhejiang Province under Grant Number:2022C02003China National Key Research and Development Plan under Grant Number:2022YFD2002303.
文摘Accurate crop disease classification is essential for disease management to support food security.Deep learning has shown its high classification accuracy in image-based disease identification.However,the deep learning approach usually needs large amounts of data for training to achieve satisfactory performance,which hindering its application and scalability for different crops.Large language models(LLMs)have shown strong generation capability and zero-shot performance.While how to utilize the LLM technique for crop disease classification remains unclear.In this study,we developed a training-free framework named ChatLeafDisease(ChatLD)based on GPT-4o model with chain-of-thought(CoT)prompting for crop disease classification.The framework includes a disease description database to provide knowledge of crop diseases and a disease classification agent guided by CoT prompts to understand the patterns of leaves infected diseases and classify the disease.The original GPT-4o model,Gemini model,and Contrastive Language-Image Pre-training(CLIP)model were chosen as baselines.Results showed that the ChatLD framework achieved higher and more stable classification accuracy(88.9%)for six tomato diseases than the GPT-4o(45.9%),Gemini(56.1%),and CLIP(64.3%)models.We found that the scoring rules enabled the ChatLD framework to capture the typical differences across diseases.Ablation results showed that the CoT prompts integrated the scoring rules and important notes to enable the ChatLD to achieve high classification accuracy.Comparison between different description texts showed that condensed disease description improved the classification performance.The results showed that the ChatLD framework achieved high accuracy for the disease classes of new crops,highlighting its scalability across various crop diseases.The proposed framework provided a new LLM-based alternative for crop disease classification by only using the textual descriptions of disease without training process.
基金supported by the National Natural Science Foundation of China(Nos.62176106 and U1836220)the Special Scientific Research Project of School of Emergency Management of Jiangsu University(No.KY-A-01)+2 种基金the Project of Faculty of Agricultural Engineering of Jiangsu University(No.NGXB20240101)the Post-graduate Research&Practice Innovation Program of Jiangsu Province(Nos.KYCX22_3668 and KYCX21_3373)the Jiangsu Key Research and Development Plan(No.BE2020036)。
文摘Semi-supervised sound event detection(SSED)tasks typically leverage a large amount of unlabeled and synthetic data to facilitate model generalization during training,reducing overfitting on a limited set of labeled data.However,the generalization training process often encounters challenges from noisy interference introduced by pseudo-labels or domain knowledge gaps.To alleviate noisy interference in class distribution learning,we propose an efficient semi-supervised class distribution learning method through dynamic prompt tuning,named prompting class distribution optimization(PADO).Specifically,when modeling real labeled data,PADO dynamically incorporates independent learnable prompt tokens to explore prior knowledge about the true distribution.Then,the prior knowledge serves as prompt information,dynamically interacting with the posterior noisy-class distribution information.In this case,PADO achieves class distribution optimization while maintaining model generalization,leading to a significant improvement in the efficiency of class distribution learning.Compared with state-of-the-art methods on the SSED datasets from DCASE 2019,2020,and 2021 challenges,PADO achieves significant performance improvements.Furthermore,it is readily extendable to other benchmark models.
基金supported by the Beijing Natural Science Foundation,China(Nos.JQ23018 and L221004)the National Natural Science Foundation of China(Nos.62036012,62072456 and 62106262)sponsored by SMP-IDATA Open Youth Fund,China.
文摘Automatic question tagging(AQT)represents a crucial task in community question answering(CQA)websites.Its pivotal role lies in substantially augmenting user experience through the optimization of question-answering efficiency.Existing question tagging models focus on the features of questions and tags,ignoring the external knowledge of the real world.Large language models can work as knowledge engines for incorporating real-world facts for different tasks.However,it is difficult for large language models to output tags in the database of CQA websites.To address this challenge,we propose a large language model enhanced question tagging method called LLMEQT to perform the question tagging task.In LLMEQT,a traditional question tagging method is first applied to pre-retrieve tags for questions.Then prompts are formulated for LLMs to comprehend the task and select more suitable tags from the candidate tags for questions.Results of our experiments on two real-world datasets demonstrate that LLMEQT significantly enhances the automatic question tagging performance for CQA,surpassing the performance of state-of-the-art methods.
基金supported in part by the China-Singapore International Joint Research Institute(CSIJRI)under Grant No.206-A023001the Undergraduate Teaching Reform Project of Shandong University under Grant Nos.2023Y235 and 2025Y99.
文摘Large language models(LLMs)show great potential in educational scenarios but face challenges like hallucination,knowledge gaps,and reasoning discontinuities.This study proposes a dynamic knowledge enhancement framework.By integrating local knowledge graphs and stepwise prompting mechanisms,it improves LLMs’accuracy and interpretability in solving professional domain problems.The framework has two core modules:an LLM-driven knowledge graph construction system for incremental updates and a unified reasoning engine for generating enhanced prompts.Experiments on 680 educational questions show that the method boosts accuracy by 4.5%and 4.3%for multi-step reasoning and knowledge-dependent questions respectively,and increases reasoning step completeness from 68.2%to 83.7%.It also reduces hallucination problems.Key contributions include the followings:①validation of an effective framework synergizing knowledge graphs with retrieval mechanisms to enhance LLM reliability;②a stepwise prompting strategy enforcing explicit reasoning chain generation,addressing pedagogical requirements for process interpretability;③a lightweight deployment solution for educational systems such as adaptive learning platforms.
文摘The springing up of large language models(LLMs)has shifted the community from single-task-orientated natural language processing(NLP)research to a holistic end-to-end multi-task learning paradigm.Along this line of research endeavors in the area,LLM-based prompting methods have attracted much attention,partially due to the technological advantages brought by prompt engineering(PE)as well as the underlying NLP principles disclosed by various prompting methods.Traditional supervised learning usually requires training a model based on labeled data and then making predictions.In contrast,PE methods directly use the powerful capabilities of existing LLMs(e.g.,GPT-3 and GPT-4)via composing appropriate prompts,especially under few-shot or zero-shot scenarios.Facing the abundance of studies related to the prompting and the ever-evolving nature of this field,this article aims to 1)illustrate a novel perspective to review existing PE methods within the well-established communication theory framework,2)facilitate a better/deeper understanding of developing trends of existing PE methods used in three typical tasks,and 3)shed light on promising research directions for future PE methods.
基金supported by 2023 Higher Education Scientific Research Planning Project of China Society of Higher Education(No.23PG0408)2023 Philosophy and Social Science Research Programs in Jiangsu Province(No.2023SJSZ0993)+2 种基金Nantong Science and Technology Project(No.JC2023070)Key Project of Jiangsu Province Education Science 14th Five-Year Plan(Grant No.B-b/2024/02/41)the Open Fund of Advanced Cryptography and System Security Key Laboratory of Sichuan Province(Grant No.SKLACSS-202407).
文摘Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.
基金supported by the National Natural Science Foundation of China(No.12105257)the Research and Development Fund(No.JMJJ202401)。
文摘The energy correlations of prompt fission neutrons have not yet been considered in the related coincidence and multiplication measurement techniques.To measure and verify the energy correlations,an experiment was performed with a total measurement duration of approximately 1200 h.In the experiment,eight CLYC detectors and sixteen EJ309 liquid scintillation detectors were utilized,and the fission moment was tagged with the measured fissionγ-rays.The relative ratios of the energy spectra of the neutrons correlated with different energy neutrons to the^(252)Cf fission neutron energy spectra were obtained.The present results may be helpful for studying fission physics and nuclear technology applications.
基金supported by the National Science and Technology Council(NSTC),Taiwan,under grant number 114-2221-E-182-041-MY3by Chang Gung University and Chang Gung Memorial Hospital under project number NERPD4Q0021.
文摘The outstanding growth in the applications of large language models(LLMs)demonstrates the significance of adaptive and efficient prompt engineering tactics.The existing methods may not be variable,vigorous and streamlined in different domains.The offered study introduces an immediate optimization outline,named PROMPTx-PE,that is going to yield a greater level of precision and strength when it comes to the assignments that are premised on LLM.The proposed systemfeatures a timely selection schemewhich is informed by reinforcement learning,a contextual layer and a dynamic weighting module which is regulated by Lyapunov-based stability guidelines.The PROMPTx-PE dynamically varies the exploration and exploitation of the prompt space,depending on real-time feedback and multi-objective reward development.Extensive testing on both benchmark(GLUE,SuperGLUE)and domain-specific data(Healthcare-QA and Industrial-NER)demonstrates a large best performance to be 89.4%and a strong robustness disconnect with under 3%computation expense.The results confirm the effectiveness,consistency,and scalability of PROMPTx-PE as a platform of adaptive prompt engineering based on recent uses of LLMs.
文摘The problem of fake news detection(FND)is becoming increasingly important in the field of natural language processing(NLP)because of the rapid dissemination of misleading information on the web.Large language models(LLMs)such as GPT-4.Zero excels in natural language understanding tasks but can still struggle to distinguish between fact and fiction,particularly when applied in the wild.However,a key challenge of existing FND methods is that they only consider unimodal data(e.g.,images),while more detailed multimodal data(e.g.,user behaviour,temporal dynamics)is neglected,and the latter is crucial for full-context understanding.To overcome these limitations,we introduce M3-FND(Multimodal Misinformation Mitigation for False News Detection),a novel methodological framework that integrates LLMs with multimodal data sources to perform context-aware veracity assessments.Our method proposes a hybrid system that combines image-text alignment,user credibility profiling,and temporal pattern recognition,which is also strengthened through a natural feedback loop that provides real-time feedback for correcting downstream errors.We use contextual reinforcement learning to schedule prompt updating and update the classifier threshold based on the latest multimodal input,which enables the model to better adapt to changing misinformation attack strategies.M3-FND is tested on three diverse datasets,FakeNewsNet,Twitter15,andWeibo,which contain both text and visual socialmedia content.Experiments showthatM3-FND significantly outperforms conventional and LLMbased baselines in terms of accuracy,F1-score,and AUC on all benchmarks.Our results indicate the importance of employing multimodal cues and adaptive learning for effective and timely detection of fake news.
基金supported by the National Key Research and Development Program of China(2023YFF0906502)the Postgraduate Research and Innovation Project of Hunan Province under Grant(CX20240473).
文摘Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural artifacts online.As an effective medium,posters serve to attract public attention and facilitate broader engagement with cultural artifacts.However,existing poster generation methods mainly rely on fixed templates and manual design,which limits their scalability and adaptability to the diverse visual and semantic features of the artifacts.Therefore,we propose CAPGen,an automated aesthetic Cultural Artifacts Poster Generation framework built on a Multimodal Large Language Model(MLLM)with integrated iterative optimization.During our research,we collaborated with designers to define principles of graphic design for cultural artifact posters,to guide the MLLM in generating layout parameters.Later,we generated these parameters into posters.Finally,we refined the posters using an MLLM integrated with a multi-round iterative optimization mechanism.Qualitative results show that CAPGen consistently outperforms baseline methods in both visual quality and aesthetic performance.Furthermore,ablation studies indicate that the prompt,iterative optimization mechanism,and design principles significantly enhance the effectiveness of poster generation.
基金supported by JSPS KAKENHI Grant Numbers JP23K28377,JP24H00714,JP25K15109,JP25K03190,JP25K03232,JP22K12157The Telecommunications Advancement Foundation.
文摘While Large Language Models(LLMs)possess the capability to perform a wide range of tasks,security attacks known as prompt injection and jailbreaking remain critical challenges.Existing defense approaches addressing this problem face challenges such as the over-refusal of prompts that contain harmful vocabulary but are semantically benign,and the limited accuracy improvement inmachine learning-based approaches due to the ease of distinguishing benign prompts in existing datasets.Therefore,we propose a multi-LLM agent framework aimed at achieving both the accurate rejection of harmful prompts and appropriate responses to benign prompts.Distinct from prior studies,the proposed method adopts In-Context Learning(ICL)during the learning phase,presenting a novel approach that obviates the need for computationally expensive parameter updates required by conventional fine-tuning.To demonstrate the proposed method’s capability for rapid and easy deployment,this study targets LLMs with insufficient alignment.In the experiments,macro-averaged binary classification metrics were used to comprehensively evaluate harmfulness detection.Experimental results using three LLMs demonstrated that the proposed method achieved performance that surpassed four baselines across all evaluation metrics for the target LLMs,evidencing significant effectiveness with an average improvement of 16.6 points in F1-score compared to the vanilla models.The significance of this study lies in the proposal of a novel approach based on ICL that does not require parameter updates.This framework offers high sustainability in practical deployment,as it allows for the adaptive enhancement of detection performance against continuously evolving attack methods solely through the accumulation of logs,without the necessity of retraining the LLM itself.By mitigating the trade-off between safety and utility,this research contributes to the implementation of robust LLMs.
