no code implementations • 5 Jun 2024 • Zhiyuan Pan, Xing Hu, Xin Xia, Xiaohu Yang
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks.
no code implementations • 25 Mar 2024 • Junkai Chen, Zhiyuan Pan, Xing Hu, Zhenhao Li, Ge Li, Xin Xia
Typically, they focus on predicting the input and output of a program, ignoring the evaluation of the intermediate behavior during program execution, as well as the logical consistency (e. g., the model should not give the correct output if the prediction of execution path is wrong) when performing the reasoning.