Stereotype Congruence Rate (SCR)¶
Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 causal),q2· 1 of 1 report an effect size · 1 claim rests on one study
Description¶
SCR is a complementary bias metric the article introduces because existing benchmarks "probe model-internal associations via templated inputs and cover only broad occupational categories", which does not suit free-text career recommendations. It is defined as "the proportion of essays in which the recommended occupation matches the biography subject's gender stereotype", with occupations labeled via BLS CPSAAT11 workforce gender shares (over 60% one gender = stereotyped; otherwise neutral). Neutral occupations count in the denominator but not as matches, making the metric conservative.
Accounts¶
- Stereotype Congruence Rate (SCR): a free-text occupational stereotyping metric grounded in BLS labor-market gender distributions: SCR is a complementary bias metric the article introduces because existing benchmarks "probe model-internal associations via templated inputs and cover only broad occupational categories", which does not suit free-text career recommendations. It is defined as "the proportion of essays in which the recommended occupation matches the biography subject's gender stereotype", with occupations labeled via BLS CPSAAT11 workforce gender shares (over 60% one gender = stereotyped; otherwise neutral). Neutral occupations count in the denominator but not as matches, making the metric conservative. (Ariyan Hossain et al. (2026))
Claims¶
Related Research Methods¶
-
Key Sources¶
- Ariyan Hossain, Kazi Kamruzzaman Rabbi, Farig Sadeque, S M Taiabul Haque. (2026). Contaminated Collaboration: Measuring Gender Bias Transfer in LLM-Assisted Student Writing. arXiv preprint. https://arxiv.org/abs/2606.15914
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
stereotype-congruence-rate-scr |
title |
Stereotype Congruence Rate (SCR) |
description |
SCR is a complementary bias metric the article introduces because existing benchmarks "probe model-internal associations via templated inputs and cover only broad occupational categories", which does not suit free-text career recommendations. |
status |
review |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.