Students solve Dafny verification exercises significantly better with ChatGPT, but the benefit depends on prompt quality and including full program context.
In: Proceedings of the 23rd ACM International Workshop on Formal Techniques for Java-like Programs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Large Language Models Help Students Prove Software Correctness? An Experimental Study with Dafny
Students solve Dafny verification exercises significantly better with ChatGPT, but the benefit depends on prompt quality and including full program context.