Publications

Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models

Junhao Liu, Haonan Yu, Zhenyu Yan, and Xin Zhang

ACL, 2026 PDF

Guiding LLM-based Loop Invariant Synthesis via Feedback on Local Reasoning Errors

Tianchi Li, Zhenyu Yan, Junhao Liu, Peng Di, and Xin Zhang

TOPLAS, will be presented on OOPSLA, 2026 PDF

Beer: Interactive Alarm Resolution in Bayesian Program Analysis via Exploration-Exploitation

Haoran Lin, Zhenyu Yan, and Xin Zhang

OOPSLA, 2026 PDF

Scaling Abstraction Refinement for Program Analyses in Datalog using Graph Neural Networks

Zhenyu Yan, Xin Zhang, and Peng Di

OOPSLA, 2024 PDF