{"title":"Toward AI-assisted Exercise Creation for First Course in Programming through Adversarial Examples of AI Models","authors":"William Chan, Y. T. Yu, J. Keung, Victor C.S. Lee","doi":"10.1109/CSEET58097.2023.00028","DOIUrl":null,"url":null,"abstract":"We propose a new methodology, the Exercise Creation Methodology (ECM), that leverages recent AI technology advancements to create ChatGPT-assisted programming exercises for beginners. ECM takes an existing exercise as input and mutates it by removing some contents into semantically equivalent but syntactically different versions. The pair of versions are labeled as answered correctly and misleadingly by ChatGPT. The removed contents are re-inserted incrementally with further mutation, ensuring the labels remain unchanged. Using the version with the misleading answer and the ChatGPT elaboration on the other version, we construct a ChatGPT-assisted exercise. The latter version may also serve as a solution. We illustrate ECM using a case study.","PeriodicalId":256885,"journal":{"name":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE 35th International Conference on Software Engineering Education and Training (CSEE&T)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CSEET58097.2023.00028","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
We propose a new methodology, the Exercise Creation Methodology (ECM), that leverages recent AI technology advancements to create ChatGPT-assisted programming exercises for beginners. ECM takes an existing exercise as input and mutates it by removing some contents into semantically equivalent but syntactically different versions. The pair of versions are labeled as answered correctly and misleadingly by ChatGPT. The removed contents are re-inserted incrementally with further mutation, ensuring the labels remain unchanged. Using the version with the misleading answer and the ChatGPT elaboration on the other version, we construct a ChatGPT-assisted exercise. The latter version may also serve as a solution. We illustrate ECM using a case study.