5 papers
VerifyThisBench: Generating Code, Specifications, and Proofs All at Once
Xun Deng, Sicheng Zhong, BarıŠBayazıt +3
Large language models (LLMs) have demonstrated remarkable progress in code generation, but many existing benchmarks are approaching saturation and offer little guarantee on the tru…
Towards Repository-Level Program Verification with Large Language Models
Si Cheng Zhong, Xujie Si
Recent advancements in large language models (LLMs) suggest great promises in code and proof generations. However, scaling automated formal verification to real-world projects requ…
RAG-Verus: Repository-Level Program Verification with LLMs using Retrieval Augmented Generation
Sicheng Zhong, Jiading Zhu, Yifang Tian +1
Scaling automated formal verification to real-world projects requires resolving cross-module dependencies and global contexts, which are challenges overlooked by existing function-…
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
Hao Tang, Keya Hu, Jin Peng Zhou +4
Iteratively improving and repairing source code with large language models (LLMs), known as refinement, has emerged as a popular way of generating programs that would be too comple…
Assessing Code Generation with Intermediate Languages
Xun Deng, Sicheng Zhong, Honghua Dong +4
Intermediate step methodologies like chain of thoughts (COT) have demonstrated effectiveness in enhancing the performance of Large Language Models (LLMs) on code generation. This s…