CodeMind: A Framework to Challenge Large Language Models for Code Reasoning

arXiv:2402.09664v1 Announce Type: cross
Abstract: Solely relying on test passing to evaluate Large Language Models (LLMs) for code synthesis may result in unfair assessment or promoting models with data leakage. As an alternative, we introduce CodeMind, a framework designed to gauge the code reasoning abilities of LLMs. CodeMind currently supports three code reasoning tasks: Independent Execution Reasoning (IER), Dependent Execution Reasoning (DER), and Specification Reasoning (SR). The first two evaluate models to predict the execution output of an arbitrary code …

abstract arxiv assessment challenge code cs.ai cs.cl cs.pl cs.se data data leakage framework language language models large language large language models llms reasoning synthesis test type