Poster
in
Workshop: MATH-AI: The 4th Workshop on Mathematical Reasoning and AI
DafnyBench: A Benchmark for Formal Software Verification
Chloe Loughridge · Qinyi Sun · Seth Ahrenbach · Federico Cassano · Chuyue (Livia) Sun · Ying Sheng · Anish Mudide · Md Rakib Hossain Misu · Nada Amin · Max Tegmark
Keywords: [ LLM ] [ formal software verification ] [ program verification ] [ Dafny ]
We introduce DafnyBench, the largest benchmark of its kind for training and evaluating machine learning systems for formal software verification. We test the ability of LLMs such as GPT-4 and Claude 3 to auto-generate enough annotations for the Dafny formal verification engine to successfully verify over 750 programs with about 53,000 lines of code. The best model and prompting scheme achieved 68% success rate, and we quantify how this rate improves when retrying with error message feedback and how it deteriorates with the amount of required code and annotations. We hope that DafnyBench will enable rapid improvements from this baseline as LLMs and verification techniques grow in quality.