← all papers · overview

Next: Teaching Large Language Models To Reason About Code Execution

Abstract

A fundamental skill among human developers is the ability to understand and reason about program execution. As an example, a programmer can mentally simulate code execution in natural language to debug and repair code (aka. rubber duck debugging). However, large language models (LLMs) of code are typically trained on the surface textual form of programs, thus may lack a semantic understanding of h

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).