7 papers
Semantic Voting: Execution-Grounded Consensus for LLM Code Generation
Shan Jiang, Zijian Yi, Chenguang Zhu
LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix textual voting, ranking, and…
Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching
Shan Jiang, Zijian Yi, Chenguang Zhu
SKETCHVERIFY is a within-tier cost-performance policy, not a universal accuracy improvement. The operational question: a practitioner stuck with a small, cheap code model (here, Ge…
OBsmith: LLM-Powered JavaScript Obfuscator Testing
Shan Jiang, Chenguang Zhu, Sarfraz Khurshid
JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performanc…
APRIL: API Synthesis with Automatic Prompt Optimization and Reinforcement Learning
Hua Zhong, Shan Jiang, Sarfraz Khurshid
APIs are central to modern software development, yet composing new APIs from large libraries is difficult due to the exponential search space; traditional component-based synthesis…
On the Effectiveness of Large Language Models in Writing Alloy Formulas
Yang Hong, Shan Jiang, Yulei Fu +1
Declarative specifications have a vital role to play in developing safe and dependable software systems. Writing specifications correctly, however, remains particularly challenging…
An approach for API synthesis using large language models
Hua Zhong, Shan Jiang, Sarfraz Khurshid
APIs play a pivotal role in modern software development by enabling seamless communication and integration between various systems, applications, and services. Component-based API…