Qingyuan Liang — accepted AI-conference papers

2025

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?

Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Xiao Yueyi +6

ACL 2025finding

Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce s…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Lyra: A Benchmark for Turducken-Style Code Generation

Qingyuan Liang, Zeyu Sun, Qihao Zhu, Wenjie Zhang, Lian Yu, Yingfei Xiong +1

IJCAI 2022poster

Recently, neural techniques have been used to generate source code automatically. While promising for declarative languages, these approaches achieve much poorer performance on datasets for imperative languages. Since a declarative language is typically embedded in an imperative language (i.e., the…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗