Evaluating LLM-Generated Code: Developer Study
Abstract
Research artefact for a paper on LLM code generation evaluation (anonymised for peer review). It contains empirical data gathered during the quality evaluation of code generated by Large Language Models for project-level code assignment. The dataset includes: PDF file with an overview of the structure of the survey CSV with anonymous results gathered from 10 developers PDF files with a summary of gathered results Markdown file with description of the questions The dataset enables reproduction of findings reported in the paper and can be reused for future LLM evaluations.
Fields of Study & Subjects
Software Engineering Research
Software Engineering Techniques and Practices
Software Testing and Debugging Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 27 February 2026
- Language
- EN
- Document type
- Dataset