生成式 AI 可用性、成绩与学生满意度：一项大型大学研究

View PDF HTML (experimental)

Abstract:The availability of generative AI (GenAI) has raised concerns that college students substitute GenAI for cognitive effort, earning high grades without learning. If this "GenAI substitution hypothesis" is true, grades should rise disproportionately in GenAI-susceptible courses--those relying more on assessments like take-home problem sets and essays rather than in-class exams. Student satisfaction (self-reported understanding and interest) may also shift. We test this hypothesis using syllabus and administrative data from a large U.S. university (2016-2025; 138,386 students; 72,730 course offerings). We measure GenAI susceptibility by extracting assessment types from syllabi with a human-validated LLM pipeline. We then use a difference-in-differences design comparing courses before and after ChatGPT's release, modeling COVID-19 effects as persistent or transient. Effects on grades and satisfaction are small and sensitive to COVID modeling choices, with no detectable differences by students' prior academic preparation. Exploratory analyses show that the link between pre-college test scores and grades has not detectably weakened in more susceptible courses, and that instructors have been making courses less susceptible since before ChatGPT. Our findings temper concerns that GenAI inflates grades and reduces satisfaction, partly because instructors may adapt their pedagogy.

Subjects:	Computers and Society (cs.CY); General Economics (econ.GN)
Cite as:	arXiv:2607.21534 [cs.CY]
	(or arXiv:2607.21534v3 [cs.CY] for this version)
	https://doi.org/10.48550/arXiv.2607.21534 arXiv-issued DOI via DataCite

Submission history

From: James Zumel Dumlao [view email]
[v1] Thu, 23 Jul 2026 17:19:55 UTC (2,780 KB)
[v2] Mon, 27 Jul 2026 18:36:14 UTC (2,781 KB)
[v3] Wed, 14 Oct 2026 17:48:25 UTC (3,057 KB)