Preprint
Aug 2026
Automatic Translation of Unstructured Requirements into Linear Temporal Logic through Large Language Models
The results indicate that current general-purpose LLMs can achieve practically significant performance on the unstructured NL-to-LTL task without task-specific fine-tuning, and suggest that modern LLMs are becoming viable front-end assistants for semi-automated formalization workflows.
Alexandra Newcomb, Omar Ochoa
· 0 citations