LLMs can generate natural language specs and perform compositional verification to help prevent vulnerable code from being produced by AI models.
Can large language models reason about program invariants? InInternational Conference on Machine Learning, pages 27496–27520
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Natural Language based Specification and Verification
LLMs can generate natural language specs and perform compositional verification to help prevent vulnerable code from being produced by AI models.