{"title":"从规范到提示：需求工程中生成式大型语言模型的未来","authors":"Andreas Vogelsang","doi":"10.1109/ms.2024.3410712","DOIUrl":null,"url":null,"abstract":"Generative LLMs, such as GPT, have the potential to revolutionize Requirements Engineering (RE) by automating tasks in new ways. This column explores the novelties and introduces the importance of precise prompts for effective interactions. Human evaluation and prompt engineering are essential in leveraging LLM capabilities.","PeriodicalId":55018,"journal":{"name":"IEEE Software","volume":"19 1","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"From Specifications to Prompts: On the Future of Generative Large Language Models in Requirements Engineering\",\"authors\":\"Andreas Vogelsang\",\"doi\":\"10.1109/ms.2024.3410712\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Generative LLMs, such as GPT, have the potential to revolutionize Requirements Engineering (RE) by automating tasks in new ways. This column explores the novelties and introduces the importance of precise prompts for effective interactions. Human evaluation and prompt engineering are essential in leveraging LLM capabilities.\",\"PeriodicalId\":55018,\"journal\":{\"name\":\"IEEE Software\",\"volume\":\"19 1\",\"pages\":\"\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-08-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Software\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1109/ms.2024.3410712\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Software","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/ms.2024.3410712","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
From Specifications to Prompts: On the Future of Generative Large Language Models in Requirements Engineering
Generative LLMs, such as GPT, have the potential to revolutionize Requirements Engineering (RE) by automating tasks in new ways. This column explores the novelties and introduces the importance of precise prompts for effective interactions. Human evaluation and prompt engineering are essential in leveraging LLM capabilities.
期刊介绍：
IEEE Software delivers reliable, useful, leading-edge software development information to keep engineers and managers abreast of rapid technology change. Its mission is to build the community of leading software practitioners. The authority on translating software theory into practice, this magazine positions itself between pure research and pure practice, transferring ideas, methods, and experiences among researchers and engineers. Peerreviewed articles and columns by seasoned practitioners illuminate all aspects of the industry, including process improvement, project management, development tools, software maintenance, Web applications and opportunities, testing, and usability. The magazine''s readers specify, design, document, test, maintain, purchase, engineer, sell, teach, research, and manage the production of software or systems that include software. IEEE Software welcomes articles describing how software is developed in specific companies, laboratories, and university environments as well as articles describing new tools, current trends, and past projects'' limitations and failures as well as successes. Sample topics include geographically distributed development; software architectures; program and system debugging and testing; the education of software professionals; requirements, design, development, testing, and management methodologies; performance measurement and evaluation; standards; program and system reliability, security, and verification; programming environments; languages and language-related issues; Web-based development; usability; and software-related social and legal issues.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
