Previous works employ the Large Language Model(LLM)like GPT-3 for knowledge-based Visual Question Answering(VQA).We argue that the inferential capacity of LLM can be enhanced through knowledge injection.Although metho...Previous works employ the Large Language Model(LLM)like GPT-3 for knowledge-based Visual Question Answering(VQA).We argue that the inferential capacity of LLM can be enhanced through knowledge injection.Although methods that utilize knowledge graphs to enhance LLM have been explored in various tasks,they may have some limitations,such as the possibility of not being able to retrieve the required knowledge.In this paper,we introduce a novel framework for knowledge-based VQA titled“Prompting Large Language Models with Knowledge-Injection”(PLLMKI).We use vanilla VQA model to inspire the LLM and further enhance the LLM with knowledge injection.Unlike earlier approaches,we adopt the LLM for knowledge enhancement instead of relying on knowledge graphs.Furthermore,we leverage open LLMs,incurring no additional costs.In comparison to existing baselines,our approach exhibits the accuracy improvement of over 1.3 and 1.7 on two knowledge-based VQA datasets,namely OK-VQA and A-OKVQA,respectively.展开更多
To illuminate the necessity of model evolvement and reuse, dynamics of injection molding machine＇s product models are analyzed. The performance knowledge is used to support the model evolvement and reuse. The driven ...To illuminate the necessity of model evolvement and reuse, dynamics of injection molding machine＇s product models are analyzed. The performance knowledge is used to support the model evolvement and reuse. The driven factors of mechanical product model are concluded. The dynamic characteristics of reuse. Finally, HT1800X1N series injection molding machines are taken as examples to illuminate that the arithmetic is correct and practical.展开更多
目的:探究中国县级公立医院医生抗菌药知识水平对抗菌药物注射剂使用率的影响,为促进中国抗菌药物注射剂合理使用提供建议。方法:通过实地调研,利用问卷对医生知识水平进行考核,收集填写问卷医生的处方以计算抗菌药物注射剂使用率,采用...目的:探究中国县级公立医院医生抗菌药知识水平对抗菌药物注射剂使用率的影响,为促进中国抗菌药物注射剂合理使用提供建议。方法:通过实地调研,利用问卷对医生知识水平进行考核,收集填写问卷医生的处方以计算抗菌药物注射剂使用率,采用描述性分析、单因素分析和广义线性回归(Generalized Linear Model,GLM)分析医生知识水平对抗菌药物注射剂使用率的影响。结果:完成8省市63家医院的350名医生的问卷调查,并收集到350份有效问卷和392 490份处方。问卷平均分为(62.8±4.1)分,具有良好的信度(Cronbachα=0.700)和效度(KMO=0.655)。GLM分析显示,不同地区(P=0.001;P=0.035)、年龄(P=0.032)、日门诊量(P=0.007)和收入(P=0.016)的医生抗菌药物注射剂使用率不同。问卷得分高的医生,抗菌药物注射剂使用率低(P=0.031)。结论:中国医生的知识水平与抗菌药物注射剂的使用率相关,不同地区、科室、性别和教育程度的医生间知识水平存在差异。应加强对西部地区和儿科医生的培训教育,这有助于改善医生的抗菌药物注射剂使用现状。展开更多
基金supported by the National Natural Science Foundation of China(No.62272100)Consulting Project of Chinese Academy of Engineering(No.2023-XY-09)Fundamental Research Funds for the Central Universities.
文摘Previous works employ the Large Language Model(LLM)like GPT-3 for knowledge-based Visual Question Answering(VQA).We argue that the inferential capacity of LLM can be enhanced through knowledge injection.Although methods that utilize knowledge graphs to enhance LLM have been explored in various tasks,they may have some limitations,such as the possibility of not being able to retrieve the required knowledge.In this paper,we introduce a novel framework for knowledge-based VQA titled“Prompting Large Language Models with Knowledge-Injection”(PLLMKI).We use vanilla VQA model to inspire the LLM and further enhance the LLM with knowledge injection.Unlike earlier approaches,we adopt the LLM for knowledge enhancement instead of relying on knowledge graphs.Furthermore,we leverage open LLMs,incurring no additional costs.In comparison to existing baselines,our approach exhibits the accuracy improvement of over 1.3 and 1.7 on two knowledge-based VQA datasets,namely OK-VQA and A-OKVQA,respectively.
基金the National Natural Science Foundation(No50505044,60573175)the Key Technology Research and Development of China(No2006BAF01A37)+1 种基金the National High Technology Research and Development Programe of China(No2007AA04Z190)the Key Scientific and Techological Research Program of Zhejiang Province(No2008C11013)
文摘To illuminate the necessity of model evolvement and reuse, dynamics of injection molding machine＇s product models are analyzed. The performance knowledge is used to support the model evolvement and reuse. The driven factors of mechanical product model are concluded. The dynamic characteristics of reuse. Finally, HT1800X1N series injection molding machines are taken as examples to illuminate that the arithmetic is correct and practical.
文摘目的:探究中国县级公立医院医生抗菌药知识水平对抗菌药物注射剂使用率的影响,为促进中国抗菌药物注射剂合理使用提供建议。方法:通过实地调研,利用问卷对医生知识水平进行考核,收集填写问卷医生的处方以计算抗菌药物注射剂使用率,采用描述性分析、单因素分析和广义线性回归(Generalized Linear Model,GLM)分析医生知识水平对抗菌药物注射剂使用率的影响。结果:完成8省市63家医院的350名医生的问卷调查,并收集到350份有效问卷和392 490份处方。问卷平均分为(62.8±4.1)分,具有良好的信度(Cronbachα=0.700)和效度(KMO=0.655)。GLM分析显示,不同地区(P=0.001;P=0.035)、年龄(P=0.032)、日门诊量(P=0.007)和收入(P=0.016)的医生抗菌药物注射剂使用率不同。问卷得分高的医生,抗菌药物注射剂使用率低(P=0.031)。结论:中国医生的知识水平与抗菌药物注射剂的使用率相关,不同地区、科室、性别和教育程度的医生间知识水平存在差异。应加强对西部地区和儿科医生的培训教育,这有助于改善医生的抗菌药物注射剂使用现状。
