Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2410.14835 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912658059427840 |
|---|---|
| author | Mukherjee, Prasita Delaware, Benjamin |
| author_facet | Mukherjee, Prasita Delaware, Benjamin |
| contents | We present \synver{}, a novel synthesis and verification framework for C programs, that deploys a Large Language Model (LLM) to search for a candidate program that satisfies the given specification. Our key idea is to impose syntactic and semantic biases on programs generated by LLMs, such that the synthesized program is more amenable to automated verification. Based on this idea, we propose a novel specification-verification tool, built on top of Verified Software Toolchain, that help automate the process. Our experiments on a diverse set of benchmarks drawn from the deductive program synthesis community, shows that this approach is scalable and extensible. The benchmarks constitute of specifications comprising of basic coding examples, Separation Logic based assertions, and API specifications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14835 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Automated Verification of LLM-Synthesized C Programs Mukherjee, Prasita Delaware, Benjamin Programming Languages We present \synver{}, a novel synthesis and verification framework for C programs, that deploys a Large Language Model (LLM) to search for a candidate program that satisfies the given specification. Our key idea is to impose syntactic and semantic biases on programs generated by LLMs, such that the synthesized program is more amenable to automated verification. Based on this idea, we propose a novel specification-verification tool, built on top of Verified Software Toolchain, that help automate the process. Our experiments on a diverse set of benchmarks drawn from the deductive program synthesis community, shows that this approach is scalable and extensible. The benchmarks constitute of specifications comprising of basic coding examples, Separation Logic based assertions, and API specifications. |
| title | Towards Automated Verification of LLM-Synthesized C Programs |
| topic | Programming Languages |
| url | https://arxiv.org/abs/2410.14835 |