Large Language Models (LLMs) have made significant progress in code generation, providing developers with unprecedented automated programming support. However, LLMs often generate code that is syntactically correct and even semantically plausible but may not execute as expected or meet specified requirements. This phenomenon of hallucinations in the code domain has not been systematically explored. To enhance the community's understanding and research on this issue, we introduce the concept of code hallucinations and propose a classification method for code hallucination based on execution verification. We classify code hallucinations into four main types: mapping, naming, resource, and logic hallucinations, with each category further divided into different subcategories to understand and address the unique challenges faced by LLMs in code generation with finer granularity. Additionally, we develop a dynamic detection algorithm named CodeHalu to quantify code hallucinations and establish the CodeHaluEval benchmark, which includes 8,883 samples from 699 tasks to systematically and quantitatively evaluate code hallucinations. By evaluating 17 popular LLMs on this benchmark, we reveal significant differences in their accuracy and reliability in code generation and provide detailed insights for further improving the code generation capabilities of LLMs. The CodeHalu benchmark and code are publicly available at https://github.com/yuchen814/CodeHalu.
翻译:暂无翻译