LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
Ziyao Zhang, Chong Wang, Yanlin Wang, Ensheng Shi, Yuchi Ma, Wanjun Zhong, Jiachi Chen, Mingzhi Mao, Zibin Zheng · 2024 · Proceedings of the ACM on Software Engineering (PACMSE / FSE)
TL;DR
Empirical study of hallucinations in repository-level code generation across six mainstream LLMs. Derives a hallucination taxonomy, distributes phenomena by model, identifies four contributing factors, and proposes an RAG-based mitigation that is effective across the studied models.
Abstract
Code generation aims to automatically generate code from input requirements, significantly enhancing development efficiency. Recent large language models (LLMs) based approaches have shown promising results and revolutionized code generation task. Despite the promising performance, LLMs often generate contents with hallucinations, especially for the code generation scenario requiring the handling of complex contextual dependencies in practical development process. Although previous study has analyzed hallucinations in LLM-powered code generation, the study is limited to standalone function generation. In this paper, we conduct an empirical study to study the phenomena, mechanism, and mitigation of LLM hallucinations within more practical and complex development contexts in repository-level generation scenario. First, we manually examine the code generation results from six mainstream LLMs to establish a hallucination taxonomy of LLM-generated code. Next, we elaborate on the phenomenon of hallucinations, analyze their distribution across different models. We then analyze causes of hallucinations and identify four potential factors contributing to hallucinations. Finally, we propose an RAG-based mitigation method, which demonstrates consistent effectiveness in all studied LLMs.
Editorial notes
Must-cite. Repository-level framing is closer to SAICA-KG's agent-context scope than function-level hallucination work. Cite as evidence that context_pollution and fabrication both intensify at repo scale and for the RAG mitigation that maps onto context-locus Tools.