In LLM-assisted team formation with name-only personas, male students are significantly less likely than female students to be assigned to Interface Design and Quality Assurance teams relative to Core Development¶

Claim · All claims
Evidence · 1 study · causal r2 · q2 · i3 large
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i3 Across three LLMs assigning name-only student personas, men are at least 80% less likely than women to be assigned to Interface Design, with the largest bias for GPT-5.2 (OR<0.01). → Erfan Entezami 2026

Evidence¶

Erfan Entezami 2026¶

Erfan Entezami, Andrew Lan, and Madeline Endres. (2026). Generative AI May Reinforce Social Biases in Software Engineering Education. arXiv preprint. https://arxiv.org/abs/2609.28483 doi:10.48550/arxiv.2609.28483

q2 · i3 · causal · r2

Controlled experiment in which GPT-4.1, GPT-5.2, and DeepSeek V3.2 assigned 1400 plain-persona assignments each; multinomial logistic regression with female and China as reference categories found "men are at least 80% less likely to be assigned toInterface Designteam than women", with the printed odds ratio OR<0.01 for GPT-5.2.

"Across all models, men are at least 80% less likely to be assigned toInterface Designteam than women, with GPT 5.2 demonstrating the largest bias (OR<0.01)."

Discussion¶

Learner Variables¶

• Gender — predictor: outcomes differ by group: a gap reflecting circumstances and treatment, not a cause

Related Claims¶

• In LLM-assisted team formation, class standing strongly drives assignments: seniors are far less likely than freshmen to be assigned to Interface Design relative to Core Development — related
• Even with skill-based qualifications, LLM team assignment remains gender-biased: when two teams are equally valid, models favor Core Development for male personas over Interface Design — related
• In LLM-assisted team formation, persona nationality systematically shifts assignments, with Nigerian names favored for Quality Assurance and South Korean names for Interface Design relative to Chinese names — related
• Learners perceived male PALs more positively and recalled more with them than with female PALs, reflecting gender stereotypes — related