{"title":"GPT 参加 SAT 考试:追踪学生考试难度和数学成绩的变化","authors":"Vikram Krishnaveti, Saannidhya Rawat","doi":"arxiv-2409.10750","DOIUrl":null,"url":null,"abstract":"Scholastic Aptitude Test (SAT) is crucial for college admissions but its\neffectiveness and relevance are increasingly questioned. This paper enhances\nSynthetic Control methods by introducing \"Transformed Control\", a novel method\nthat employs Large Language Models (LLMs) powered by Artificial Intelligence to\ngenerate control groups. We utilize OpenAI's API to generate a control group\nwhere GPT-4, or ChatGPT, takes multiple SATs annually from 2008 to 2023. This\ncontrol group helps analyze shifts in SAT math difficulty over time, starting\nfrom the baseline year of 2008. Using parallel trends, we calculate the Average\nDifference in Scores (ADS) to assess changes in high school students' math\nperformance. Our results indicate a significant decrease in the difficulty of\nthe SAT math section over time, alongside a decline in students' math\nperformance. The analysis shows a 71-point drop in the rigor of SAT math from\n2008 to 2023, with student performance decreasing by 36 points, resulting in a\n107-point total divergence in average student math performance. We investigate\npossible mechanisms for this decline in math proficiency, such as changing\nuniversity selection criteria, increased screen time, grade inflation, and\nworsening adolescent mental health. Disparities among demographic groups show a\n104-point drop for White students, 84 points for Black students, and 53 points\nfor Asian students. Male students saw a 117-point reduction, while female\nstudents had a 100-point decrease.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"195 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"GPT takes the SAT: Tracing changes in Test Difficulty and Math Performance of Students\",\"authors\":\"Vikram Krishnaveti, Saannidhya Rawat\",\"doi\":\"arxiv-2409.10750\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Scholastic Aptitude Test (SAT) is crucial for college admissions but its\\neffectiveness and relevance are increasingly questioned. This paper enhances\\nSynthetic Control methods by introducing \\\"Transformed Control\\\", a novel method\\nthat employs Large Language Models (LLMs) powered by Artificial Intelligence to\\ngenerate control groups. We utilize OpenAI's API to generate a control group\\nwhere GPT-4, or ChatGPT, takes multiple SATs annually from 2008 to 2023. This\\ncontrol group helps analyze shifts in SAT math difficulty over time, starting\\nfrom the baseline year of 2008. Using parallel trends, we calculate the Average\\nDifference in Scores (ADS) to assess changes in high school students' math\\nperformance. Our results indicate a significant decrease in the difficulty of\\nthe SAT math section over time, alongside a decline in students' math\\nperformance. The analysis shows a 71-point drop in the rigor of SAT math from\\n2008 to 2023, with student performance decreasing by 36 points, resulting in a\\n107-point total divergence in average student math performance. We investigate\\npossible mechanisms for this decline in math proficiency, such as changing\\nuniversity selection criteria, increased screen time, grade inflation, and\\nworsening adolescent mental health. Disparities among demographic groups show a\\n104-point drop for White students, 84 points for Black students, and 53 points\\nfor Asian students. Male students saw a 117-point reduction, while female\\nstudents had a 100-point decrease.\",\"PeriodicalId\":501293,\"journal\":{\"name\":\"arXiv - ECON - Econometrics\",\"volume\":\"195 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - ECON - Econometrics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.10750\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - ECON - Econometrics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.10750","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
GPT takes the SAT: Tracing changes in Test Difficulty and Math Performance of Students
Scholastic Aptitude Test (SAT) is crucial for college admissions but its
effectiveness and relevance are increasingly questioned. This paper enhances
Synthetic Control methods by introducing "Transformed Control", a novel method
that employs Large Language Models (LLMs) powered by Artificial Intelligence to
generate control groups. We utilize OpenAI's API to generate a control group
where GPT-4, or ChatGPT, takes multiple SATs annually from 2008 to 2023. This
control group helps analyze shifts in SAT math difficulty over time, starting
from the baseline year of 2008. Using parallel trends, we calculate the Average
Difference in Scores (ADS) to assess changes in high school students' math
performance. Our results indicate a significant decrease in the difficulty of
the SAT math section over time, alongside a decline in students' math
performance. The analysis shows a 71-point drop in the rigor of SAT math from
2008 to 2023, with student performance decreasing by 36 points, resulting in a
107-point total divergence in average student math performance. We investigate
possible mechanisms for this decline in math proficiency, such as changing
university selection criteria, increased screen time, grade inflation, and
worsening adolescent mental health. Disparities among demographic groups show a
104-point drop for White students, 84 points for Black students, and 53 points
for Asian students. Male students saw a 117-point reduction, while female
students had a 100-point decrease.