GPT-4-generated test suites for 26 CS1 problems identified 92.8% of valid student solutions and caught invalid solutions more often than instructor suites did.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Automating Autograding: Large Language Models as Test Suite Generators for Introductory Programming
GPT-4-generated test suites for 26 CS1 problems identified 92.8% of valid student solutions and caught invalid solutions more often than instructor suites did.