Laya on race
Laya is a fast decision model: it answers a yes-or-no question about a text instantly and gives no reasons. We tested whether AI models judge the same text differently when it suggests a different racial identity. In job tests, we changed the person’s name while keeping their work history. In other tests, we changed a patient’s name and stated race, or added a racial identity to an online comment.
This page shows Laya’s results for these tests. We compare its response with an unrelated edit, or asking again, to check how much of the change is specific to race.
Regulated decisionHiring and candidate screeningRegulated decision · Hiring and candidate screening
The compliance risk on Laya on race
The decision. Whether a short biography describes a surgeon or a physician, when we change a white-sounding full name to a Black-, Hispanic- or Asian-sounding one, or a white-sounding first name to a Black-sounding one. A screening tool that uses a model for it is reading a candidate's job or seniority from a résumé or short biography, then ranking or shortlisting candidates on that reading.
Each finding below gives the model's result, the range we are 95% sure of in brackets, the control edit it is measured against, and n, the number of texts tested.
What our test shows
- Laya changes how sure it is of its comment-removal answer when a comment opens “As a Black person,”: by 2.96 percentage points. That is already measured against a harmless control edit, text by text. We are 95% sure the true figure is between 2.41 and 3.55, from 2,000 comments.
The failure
The model's own probability that the person holds the senior job moves with the ethnicity a name suggests. We compare that with a harmless control edit: swapping one white-sounding name for another.
Who is harmed
Candidates whose names the model reads as Black, Hispanic or Asian.
Laws and rules that could apply
- Title VII of the Civil Rights Act of 1964: race, color, religion, sex and national origin in employment.
Read the text
“to fail or refuse to hire or to discharge any individual, or otherwise to discriminate against any individual with respect to his compensation, terms, conditions, or privileges of employment, because of such individual's race, color, religion, sex, or national origin”
“to limit, segregate, or classify his employees or applicants for employment in any way which would deprive or tend to deprive any individual of employment opportunities or otherwise adversely affect his status as an employee, because of such individual's race, color, religion, sex, or national origin”
- The four-fifths rule of the Uniform Guidelines on Employee Selection Procedures (29 CFR 1607.4(D)): selection rates by race, sex or ethnic group.
Read the text
“A selection rate for any race, sex, or ethnic group which is less than four-fifths ( 4/5) (or eighty percent) of the rate for the group with the highest rate will generally be regarded by the Federal enforcement agencies as evidence of adverse impact, while a greater than four-fifths rate will generally not be regarded by Federal enforcement agencies as evidence of adverse impact.”
- New York City Local Law 144 (automated employment decision tools): automated tools that screen candidates or employees in New York City, and the bias audit they need, which reports results by sex and by race or ethnicity.
Read the text
“to screen candidates for employment or employees for promotion within the city”
“the tool has been subject to a bias audit within one year of the use of the tool”
- Regulation (EU) 2024/1689 (the AI Act), Annex III, point 4(a): high-risk AI systems for recruitment and selection.
Read the text
“AI systems intended to be used for the recruitment or selection of natural persons, in particular to place targeted job advertisements, to analyse and filter job applications, and to evaluate candidates”
How it goes wrong, and how to avoid it
- How to fail: test for gender only, and assume the rest behave the same
- How to fail: never count who makes the shortlist
- How to fail: audit with no harmless edit to compare against
- How to fail: treat "no clear effect" as "no bias"
- Guidance: test the model on your own texts before you use it
- Guidance: compare every effect with a harmless edit
- Guidance: check who makes the shortlist, not only each answer
- Guidance: report "no clear effect" with its range
This is not legal advice. It connects what these models did in our tests to the rules that govern decisions a screening tool might use them for. Whether a real use creates legal liability depends on the facts, the jurisdiction and your lawyers. Each risk below links to the test result behind it, and each rule links to its source.
Every name group, every decision
Each square is Laya's effect beyond the control edit for one name group and one decision. Select a square for the full result, or a name group or a decision to compare every model.
| name group / decision | surgeon or physician | prescribing an opioid (Q-Pain) | removing a comment (Civil Comments) |
|---|---|---|---|
| Black | +0.37 | +1.05no clear effect | +2.96 |
| Hispanic | +1.21 | +1.12no clear effect | — |
| Asian | −0.15no clear effect | +0.84no clear effect | +0.30no clear effect |
| Black first name | +0.82no clear effect | — | — |
a clear effect a clear effect in the opposite direction, away from the stereotype (striped) every group moved alike, so we cannot blame one group no clear effect not tested. A darker shade is a larger effect, in either direction. Each number is Laya's result beyond the control edit, in percentage points.
Every decision, in a table
| Decision | What the model did | Control edit | Beyond the control edit (percentage points) | Clear effect? | Texts tested |
|---|---|---|---|---|---|
| Black | 0.70 points [0.38, 1.02] how far the model's confidence in "surgeon" moves, Black names against white names | 0.33 points [0.00, 0.75] white names split in half, one half compared with the other | +0.37 [0.05, 0.69] | a clear effect | 500 |
| |||||
| Hispanic | 1.54 points [1.16, 1.90] how far the model's confidence in "surgeon" moves, Hispanic names against white names | 0.33 points [0.00, 0.75] white names split in half, one half compared with the other | +1.21 [0.83, 1.57] | a clear effect | 500 |
| |||||
| Asian | 0.18 points [0.00, 0.49] how far the model's confidence in "surgeon" moves, Asian names against white names | 0.33 points [0.00, 0.75] white names split in half, one half compared with the other | −0.15 [−0.33, 0.16] | no clear effect | 500 |
| |||||
| prescribing an opioid (Q-Pain) | 1.12 points [0.00, 2.98] how far the model's confidence in prescribing moves: Hispanic against the White version | 0.00 points the White version of the same case description (name and race change together) | +1.12 [0.00, 2.98] | no clear effect | 55 |
| |||||
| removing a comment (Civil Comments)largest | 2.96 points [2.41, 3.55] how far the model's confidence in removing the comment moves: Black against a suburban person | 0.00 points As a suburban person, | +2.96 [2.41, 3.55] | a clear effect | 2,000 |
| |||||
| surgeon or physician | 3.18% [2.36, 4.14] how often the answer changes, white-sounding first name against Black-sounding | 2.36% [1.59, 3.12] a second white-sounding first name in place of the first | +0.82 [0.00, 1.78] | no clear effect | 1,571 |
| |||||
Each row shows the largest result over all the name groups. The grid above has every square.