Retrieval-augmented prompting improves LLM proof-completion pass rates by 27% relative on a new repository-level Verus benchmark and triples them on a function-level benchmark at low sampling budgets.
Selene: Pioneering Automated Proof in Software Verification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Ensuring correctness is a pivotal aspect of software engineering. Among the various strategies available, software verification offers a definitive assurance of correctness. Nevertheless, writing verification proofs is resource-intensive and manpower-consuming, and there is a great need to automate this process. We introduce Selene in this paper, which is the first project-level automated proof benchmark constructed based on the real-world industrial-level operating system microkernel, seL4. Selene provides a comprehensive framework for end-to-end proof generation and a lightweight verification environment. Our experimental results with advanced large language models (LLMs), such as GPT-3.5-turbo and GPT-4, highlight the capabilities of LLMs in the domain of automated proof generation. Additionally, our further proposed augmentations indicate that the challenges presented by Selene can be mitigated in future research endeavors.
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RAG-Verus: Repository-Level Program Verification with LLMs using Retrieval Augmented Generation
Retrieval-augmented prompting improves LLM proof-completion pass rates by 27% relative on a new repository-level Verus benchmark and triples them on a function-level benchmark at low sampling budgets.