Saved in:
Bibliographic Details
Main Authors: Li, Zhaorui, Song, Chengyu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.11315
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916003356606464
author Li, Zhaorui
Song, Chengyu
author_facet Li, Zhaorui
Song, Chengyu
contents Recent frontier large language models (LLMs) have shown strong performance in identifying security vulnerabilities in large, mature open-source systems. As LLM-generated code becomes increasingly common, a natural goal is to prevent such models from producing vulnerable implementations in the first place. Formal verification offers a principled route to this objective, but existing verification pipelines typically require specifications written in rigid formal languages. Prior work has explored using LLMs to synthesize such specifications, with limited success. In this paper, we investigate a different approach: using LLMs both to generate specifications and to verify implementations compositionally when the specifications are expressed in natural language. Our preliminary results suggest that this approach is promising.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11315
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Natural Language based Specification and Verification
Li, Zhaorui
Song, Chengyu
Software Engineering
Artificial Intelligence
Cryptography and Security
Recent frontier large language models (LLMs) have shown strong performance in identifying security vulnerabilities in large, mature open-source systems. As LLM-generated code becomes increasingly common, a natural goal is to prevent such models from producing vulnerable implementations in the first place. Formal verification offers a principled route to this objective, but existing verification pipelines typically require specifications written in rigid formal languages. Prior work has explored using LLMs to synthesize such specifications, with limited success. In this paper, we investigate a different approach: using LLMs both to generate specifications and to verify implementations compositionally when the specifications are expressed in natural language. Our preliminary results suggest that this approach is promising.
title Natural Language based Specification and Verification
topic Software Engineering
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2605.11315