Evaluating the Impact of AI-Generated Hallucinated Code on Software Reliability: A Systematic Literature Review
Abstract
This is a self-archived systematic literature review on AI-generated hallucinated code and its effect on software reliability, deposited here ahead of peer review. It draws on about 20 papers covering hallucination taxonomy and detection, mitigation approaches such as self-refinement and retrieval-augmented generation, code-focused language models, and related evaluation benchmarks, with Lee et al.'s 2025 survey as the main anchor. The purpose of this deposit is to timestamp the work and make it citable while formal submission is still in progress. Comments and corrections are welcome.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.