遇见数据集

NL2VBENCH

收藏
Zenodo2026-07-03 更新2026-08-01 收录
官方服务:

资源简介:

NL2VBench is a benchmark dataset for evaluating LLMs on generating Verus-verified Rust programs from natural language descriptions. It contains 762 curated tasks across 3 categories (Simple, Loops, Complex). Each task includes a natural-language description, function signature, and a reference verified Verus implementation. The artifact also includes 12 prompt templates, experiment scripts, and a verification script.

提供机构:
Zenodo
创建时间:
2026-07-03
二维码
社区交流群
二维码
科研交流群
商业服务