Objective: Smoking cessation during pregnancy is a modifiable intervention that can improve maternal and neonatal outcomes. Encouraging smoking cessation is an assessed measure of the Meaningful Use incentives to ensu...Objective: Smoking cessation during pregnancy is a modifiable intervention that can improve maternal and neonatal outcomes. Encouraging smoking cessation is an assessed measure of the Meaningful Use incentives to ensure best practices with the increased use of the electronic medical record (EMR). Physician EMR prompts have been used shown to be successful with preventive care but there is a paucity of data evaluating prompts within obstetrics. The objective of this study is to determine the effectiveness of enhanced smoking cessation prompts in a prenatal EMR. Methods: A retrospective cohort study of an enhanced smoking cessation prompting system within our prenatal EMR was performed. Pregnant women who reported tobacco use at first prenatal visit were included. The number of times a smoking cessation method was offered and documented, the number of documented attempts at smoking cessation, and the final number of cigarettes smoked were compared pre and post the enhancement of the smoking cessation prompting system. Results: 95 patients were included (48 pre-enhancement;47 post-enhancement). Post-enhancement, the documentation of smoking cessation method offered increased (0 vs. 1, p = 0.03) and documentation of smoking cessation attempts increased (1 vs. 2, p = 0.006). There was no change in the final number of cigarettes smoked (p = 0.9). Conclusions: Enhanced prompting systems increase documentation related to smoking cessation with no change in number of cigarettes smoked. In the era of Meaningful Use guidelines which focus on documentation in the EMR, continued research must be done to assure that software enhancements and improved documentation truly result in improved patient care.展开更多
In recent years,the rapid advancements of Large Language Models(LLMs)such as ChatGPT and GPT-5 have ushered machine translation into a new era.This study examines the impact of different prompts-simple prompts,complex...In recent years,the rapid advancements of Large Language Models(LLMs)such as ChatGPT and GPT-5 have ushered machine translation into a new era.This study examines the impact of different prompts-simple prompts,complex prompts,and few-shot prompts-on GPT-5's translation performance for the 2024 Chinese Government Work Report,finding that while complex prompts yielded better results in automatic evaluation metrics,human assessment showed no substantial differences in translation quality between simple and complex prompts.The few-shot prompting approach displayed potential in adapting to the text style,but still faced common machine translation challenges,underscoring the importance of thoroughly analyzing text requirements and providing targeted prompt instructions when utilizing large language models for translation,as well as the need for future translators to master the characteristics of these models and develop the ability to identify and adjust translation issues,in order to enhance the practical effectiveness of machine translation.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
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
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 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 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
Dear Editor,Chibanian(Middle Pleistocene)hominin fossils that could not be easily assigned to Homo erectus,H.neanderthalensis,or H.sapiens have traditionally been as-signed to an alinclusive group:"archaic H.sapi...Dear Editor,Chibanian(Middle Pleistocene)hominin fossils that could not be easily assigned to Homo erectus,H.neanderthalensis,or H.sapiens have traditionally been as-signed to an alinclusive group:"archaic H.sapiens."In an insightful observation of the Chibanian record almost four decades ago however,Tattersall railed against the use of the word"archaic"in this sense when referring to the human fossil record,as he justifiably noted that no other biological organism has the word"archaic"attached to it'For example,no one refers to an earlier version of Canis domesticus as"archaic"C.domesticus.The ancestor of the domestic dog is,and always has been,considered to be C.lupus.In Tattersall's opinion,it would seem that these"archaic H.sapiens"fossils should be assigned to one or more formal taxonomic names.As such,terms such as"archaic H.sapiens,""mid-Pleistocene Homo,"and"Middle Pleistocene Homo"have al-ways been considered to be wastebasket taxa that include way too much morphological variabilty for one proposed taxonomic group.Continuing to use wastebasket taxa only hinders any attempts to understand true phylogenetic and evolutionary relationships.展开更多
Image emotion classification(IEC)aims to extract the abstract emotions evoked in images.Recently,language-supervised methods such as con-trastive language-image pretraining(CLIP)have demonstrated superior performance ...Image emotion classification(IEC)aims to extract the abstract emotions evoked in images.Recently,language-supervised methods such as con-trastive language-image pretraining(CLIP)have demonstrated superior performance in image under-standing.However,the underexplored task of IEC presents three major challenges:a tremendous training objective gap between pretraining and IEC,shared suboptimal prompts,and invariant prompts for all instances.In this study,we propose a general framework that effectively exploits the language-supervised CLIP method for the IEC task.First,a prompt-tuning method that mimics the pretraining objective of CLIP is introduced,to exploit the rich image and text semantics associated with CLIP.Subsequently,instance-specific prompts are automatically composed,conditioning them on the categories and image content of instances,diversifying the prompts,and thus avoiding suboptimal problems.Evaluations on six widely used affective datasets show that the proposed method significantly outperforms state-of-the-art methods(up to 9.29%accuracy gain on the EmotionROI dataset)on IEC tasks with only a few trained parameters.The code is publicly available at https://github.com/dsn0w/PT-DPC/for research purposes.展开更多
ChatGPT has emerged as a promising advanced large language model that needs prompt to gain information.However,designing a good prompt is not an easy task for many end-users.Therefore,this study intends to determine t...ChatGPT has emerged as a promising advanced large language model that needs prompt to gain information.However,designing a good prompt is not an easy task for many end-users.Therefore,this study intends to determine the amount of information gained because of varied amounts of information in the prompt.This study used two types of prompts,initial and improved,to query the introduction sections of 327 highly cited articles on traffic safety.The queried introduction sections were then matched with the corresponding human-written introduction sections from the same articles.Similarity tests and text network analysis were used to understand the level of similarities and the content of ChatGPT-generated and human-written introductions.The findings indicate the improved prompts,which have the addition of generic persona and information about the citations and references,changed the ChatGPT's output insignificantly.While the perfect similar contents are supposed to have a 1.0 similarity score,the initial and improved prompt's introduction materials have average similarity scores of 0.5387 and 0.5567,respectively.Further,the content analysis revealed that themes such as statistics,trends,safety measures,and safety technologies are more likely to have high similarity scores,irrespective of the amount of information provided in the prompt.On the other hand,themes such as human behavior,policy and regulations,public perception,and emerging technologies require a detailed level of information in their prompt to produce materials that are close to human-written materials.The prompt engineers can use the findings to evaluate their outputs and improve their prompting skills.展开更多
Artificial intelligence(AI)is advancing swiftly and integrating into various societal domains,including international Chinese language teaching.While AI provides diverse advantages,it also presents inherent risks,akin...Artificial intelligence(AI)is advancing swiftly and integrating into various societal domains,including international Chinese language teaching.While AI provides diverse advantages,it also presents inherent risks,akin to a“double-edged sword”.This paper delves into the challenges and opportunities associated with AI and suggests a strategy to transform AI from a potential adversary to an ally:not avoidance,but mastery.Mastery entails crafting targeted prompts suitable for distinct contexts to attain desired AI-driven outcomes.Ultimately,by presenting case studies across various proficiency levels in Chinese language instruction that utilize AI tools,this paper aims to stimulate constructive dialogue within the academic community of Chinese language teaching.展开更多
文摘Objective: Smoking cessation during pregnancy is a modifiable intervention that can improve maternal and neonatal outcomes. Encouraging smoking cessation is an assessed measure of the Meaningful Use incentives to ensure best practices with the increased use of the electronic medical record (EMR). Physician EMR prompts have been used shown to be successful with preventive care but there is a paucity of data evaluating prompts within obstetrics. The objective of this study is to determine the effectiveness of enhanced smoking cessation prompts in a prenatal EMR. Methods: A retrospective cohort study of an enhanced smoking cessation prompting system within our prenatal EMR was performed. Pregnant women who reported tobacco use at first prenatal visit were included. The number of times a smoking cessation method was offered and documented, the number of documented attempts at smoking cessation, and the final number of cigarettes smoked were compared pre and post the enhancement of the smoking cessation prompting system. Results: 95 patients were included (48 pre-enhancement;47 post-enhancement). Post-enhancement, the documentation of smoking cessation method offered increased (0 vs. 1, p = 0.03) and documentation of smoking cessation attempts increased (1 vs. 2, p = 0.006). There was no change in the final number of cigarettes smoked (p = 0.9). Conclusions: Enhanced prompting systems increase documentation related to smoking cessation with no change in number of cigarettes smoked. In the era of Meaningful Use guidelines which focus on documentation in the EMR, continued research must be done to assure that software enhancements and improved documentation truly result in improved patient care.
文摘In recent years,the rapid advancements of Large Language Models(LLMs)such as ChatGPT and GPT-5 have ushered machine translation into a new era.This study examines the impact of different prompts-simple prompts,complex prompts,and few-shot prompts-on GPT-5's translation performance for the 2024 Chinese Government Work Report,finding that while complex prompts yielded better results in automatic evaluation metrics,human assessment showed no substantial differences in translation quality between simple and complex prompts.The few-shot prompting approach displayed potential in adapting to the text style,but still faced common machine translation challenges,underscoring the importance of thoroughly analyzing text requirements and providing targeted prompt instructions when utilizing large language models for translation,as well as the need for future translators to master the characteristics of these models and develop the ability to identify and adjust translation issues,in order to enhance the practical effectiveness of machine translation.
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 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 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.
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.
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National Natural Science Foundation of China Grant 42372001.
文摘Dear Editor,Chibanian(Middle Pleistocene)hominin fossils that could not be easily assigned to Homo erectus,H.neanderthalensis,or H.sapiens have traditionally been as-signed to an alinclusive group:"archaic H.sapiens."In an insightful observation of the Chibanian record almost four decades ago however,Tattersall railed against the use of the word"archaic"in this sense when referring to the human fossil record,as he justifiably noted that no other biological organism has the word"archaic"attached to it'For example,no one refers to an earlier version of Canis domesticus as"archaic"C.domesticus.The ancestor of the domestic dog is,and always has been,considered to be C.lupus.In Tattersall's opinion,it would seem that these"archaic H.sapiens"fossils should be assigned to one or more formal taxonomic names.As such,terms such as"archaic H.sapiens,""mid-Pleistocene Homo,"and"Middle Pleistocene Homo"have al-ways been considered to be wastebasket taxa that include way too much morphological variabilty for one proposed taxonomic group.Continuing to use wastebasket taxa only hinders any attempts to understand true phylogenetic and evolutionary relationships.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.62106010,61976010,62176011,62236010.
文摘Image emotion classification(IEC)aims to extract the abstract emotions evoked in images.Recently,language-supervised methods such as con-trastive language-image pretraining(CLIP)have demonstrated superior performance in image under-standing.However,the underexplored task of IEC presents three major challenges:a tremendous training objective gap between pretraining and IEC,shared suboptimal prompts,and invariant prompts for all instances.In this study,we propose a general framework that effectively exploits the language-supervised CLIP method for the IEC task.First,a prompt-tuning method that mimics the pretraining objective of CLIP is introduced,to exploit the rich image and text semantics associated with CLIP.Subsequently,instance-specific prompts are automatically composed,conditioning them on the categories and image content of instances,diversifying the prompts,and thus avoiding suboptimal problems.Evaluations on six widely used affective datasets show that the proposed method significantly outperforms state-of-the-art methods(up to 9.29%accuracy gain on the EmotionROI dataset)on IEC tasks with only a few trained parameters.The code is publicly available at https://github.com/dsn0w/PT-DPC/for research purposes.
文摘ChatGPT has emerged as a promising advanced large language model that needs prompt to gain information.However,designing a good prompt is not an easy task for many end-users.Therefore,this study intends to determine the amount of information gained because of varied amounts of information in the prompt.This study used two types of prompts,initial and improved,to query the introduction sections of 327 highly cited articles on traffic safety.The queried introduction sections were then matched with the corresponding human-written introduction sections from the same articles.Similarity tests and text network analysis were used to understand the level of similarities and the content of ChatGPT-generated and human-written introductions.The findings indicate the improved prompts,which have the addition of generic persona and information about the citations and references,changed the ChatGPT's output insignificantly.While the perfect similar contents are supposed to have a 1.0 similarity score,the initial and improved prompt's introduction materials have average similarity scores of 0.5387 and 0.5567,respectively.Further,the content analysis revealed that themes such as statistics,trends,safety measures,and safety technologies are more likely to have high similarity scores,irrespective of the amount of information provided in the prompt.On the other hand,themes such as human behavior,policy and regulations,public perception,and emerging technologies require a detailed level of information in their prompt to produce materials that are close to human-written materials.The prompt engineers can use the findings to evaluate their outputs and improve their prompting skills.
文摘Artificial intelligence(AI)is advancing swiftly and integrating into various societal domains,including international Chinese language teaching.While AI provides diverse advantages,it also presents inherent risks,akin to a“double-edged sword”.This paper delves into the challenges and opportunities associated with AI and suggests a strategy to transform AI from a potential adversary to an ally:not avoidance,but mastery.Mastery entails crafting targeted prompts suitable for distinct contexts to attain desired AI-driven outcomes.Ultimately,by presenting case studies across various proficiency levels in Chinese language instruction that utilize AI tools,this paper aims to stimulate constructive dialogue within the academic community of Chinese language teaching.
