Standing on Shoulders
This research builds on decades of work documenting how names influence treatment. We acknowledge and integrate that scholarship here.
The patterns we detect in AI are not novel. They reflect biases documented across fifty years of social science research. Every citation is a debt acknowledged.
I. The Naming Problem (1960s–2000s)
Names carry demographic signals that influence how people are treated.
Bertrand & Mullainathan
The seminal study. Identical resumes with names signaling different racial backgrounds received dramatically different callback rates. Emily and Greg received 50% more callbacks than Lakisha and Jamal.
Fryer & Levitt
Validated the demographic associations of names. Established which names reliably signal racial and ethnic identity in American contexts.
Cotton, O'Neill & Griffin
Extended name research to first names. Demonstrated that name characteristics (not just racial associations) influence professional evaluations.
Laham, Koval & Alter
The name-pronunciation effect. People judge others more favorably when their names are easier to pronounce—a phonetic basis for bias.
II. Healthcare Disparities (1990s–2010s)
Demographic indicators systematically influence medical treatment decisions.
Schulman et al.
Race and sex affect physicians' cardiac catheterization recommendations. The same symptoms, different referral rates. A landmark NEJM study.
Strakowski et al.
Racial disparities in psychiatric diagnosis from emergency services. Schizophrenia diagnosed more frequently in Black patients presenting with identical symptoms.
Hoffman et al.
Racial bias in pain assessment. Medical students and residents endorsed false beliefs about biological differences and recommended less pain treatment for Black patients.
III. Algorithmic Bias (2010s–Present)
AI systems inherit and amplify human biases at scale.
Bolukbasi et al.
Word embeddings encode gender bias. "Man is to computer programmer as woman is to homemaker." The mathematical representations of language carry our biases.
ProPublica (Angwin et al.)
COMPAS criminal justice algorithm biased against Black defendants. Investigative journalism that brought algorithmic bias into public discourse.
Caliskan, Bryson & Narayanan
Semantics derived from language corpora contain human-like biases. AI learns our prejudices from the text it reads.
Buolamwini & Gebru
Gender Shades. Commercial facial recognition systems had error rates up to 34.7% higher for darker-skinned women than lighter-skinned men. Intersectional disparities in AI.
Obermeyer et al.
Racial bias in a healthcare algorithm affecting millions. A widely-used algorithm systematically discriminated against Black patients by using cost as a proxy for health need.
Bender et al.
"On the Dangers of Stochastic Parrots." Comprehensive analysis of risks in large language models, including bias propagation and the illusion of understanding.
IV. The Gap We Address
Prior research established that:
- Names carry demographic signals that influence treatment (Bertrand & Mullainathan)
- Healthcare decisions systematically differ by demographic indicators (Hoffman, Schulman)
- AI systems inherit and amplify human biases (Obermeyer, Buolamwini)
But this work focused primarily on content—what AI systems say, what treatments they recommend, what predictions they make.
We asked a different question:
Does bias persist in the structure of AI-generated text—the mathematical patterns of how responses unfold—even when vocabulary appears neutral?
The answer, documented in our evidence section, is yes. Structural analysis reveals patterns invisible to content analysis.
Our Contribution
We developed methods to detect bias in narrative structure—12 dimensions of analysis that reveal how AI-generated text unfolds differently based on name signals. Methodology details forthcoming in academic publication.
Continue exploring the research
See the Evidence