Metraipolis › archive › dc_5ca12409ffa3
When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation — arXiv:2609.22102
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22102
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:50:20.053Z
- SHA-256 of the archived text
21dd64c626b8e02616cd074a9147eb69a6fc52f267d8418b300b013387bdca33- Stable URL of this page
https://metraipolis.com/documento/dc_5ca12409ffa3
How to cite
When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation — arXiv:2609.22102 — arXiv (en), https://arxiv.org/abs/2609.22102 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ca12409ffa3 (Metraipolis archive dc_5ca12409ffa3, sha256 21dd64c626b8e02616cd074a9147eb69a6fc52f267d8418b300b013387bdca33)
BibTeX
@misc{dc5ca12409ffa3,
title = {When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation — arXiv:2609.22102},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22102},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ca12409ffa3; sha256 21dd64c626b8e02616cd074a9147eb69a6fc52f267d8418b300b013387bdca33},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22102. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts the technical quality of generated code. We conduct a large-scale empirical study of persona-induced bias in LLM-based code generation, focusing a proprietary model (Gemini 2.5 Pro) and an open-weight model (GPT-OSS-120B). Using 18 demographic personas spanning nationality, gender, and experience level, we compare persona-induced prompts against a neutral baseline. Across 35,000+ generated programs, we analyze demographic marker leakage in reasoning and responses, as well as differences in functional correctness, maintainability, code style, and security. Our results show that demographic cues are frequently reflected in LLM reasoning and outputs. Demographic markers appear in up to 65% of responses and 70% of reasoning traces, despite being semantically irrelevant to the tasks. On LiveCodeBench, persona prompting were associated with lower correctness scores of the Gemini model by an average of 1.54 percentage points, with one persona exhibiting a decrease of 3.6% (odds ratio = 0.51). In contrast, the accuracy of the GPT-OSS model improved by 3.4 - 5.7% across all personas (odds ratios = 1.8 - 3.0). Maintainability and code style metrics show statistically significant but negligible effect sizes (all Cliff's {\delta} < 0.15), and security vulnerabilities exhibit no systematic persona-specific patterns. Overall, our results show that the presence of demographic information about users is associated with measurable variation in LLM reasoning and code quality even in purely technical tasks, and that these effects hold across models. Our work highlights an under-examined risk in LLM-assisted software development.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Software Engineering (cs.SE) ; Computation and Language (cs.CL); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.22102 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:48:45.081Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).