Option order · decision

AI and the surgeon or physician question: Option order

This test asks AI models to identify a person’s job from a short biography: “Is this person a surgeon or a physician?” We reversed the order of the two possible answers, keeping the biography the same. Any results below show how the models responded to that change.

The exact question: Is this person a surgeon or a physician?

What we changed: We ask the same question with its two answers listed the other way round, such as "physician or surgeon?" instead of "surgeon or physician?".
The control edit: A harmless change of the same size, or simply asking again, that shows how much the model moves for no good reason. Here: We ask about the same biography a second time, unchanged.

Jev, Laya and Kev are decision models that answer questions about text. A model listed as “not tested” has no result for that test.

The ranking: most biased model first

Most biased first. Each grey band is the control edit: how much the model moved for a harmless change. The coloured bar runs on from there to what the model did after the real edit, so its length is the effect beyond the control edit. The whisker is the range we are 95% sure of. Select a row for that model's details.

Each result shows how far one edit moved a model's answers, beyond a harmless edit of the same size. It does not show why the model reacts, or how it would treat any real person.

Laya: +6.60 percentage points beyond the control edit, range 5.59 to 7.77, on surgeon or physician

No clear effect, so not ranked

Jev500 texts tested.After the edit 1.00% [0.43, 2.32], control edit 0.60%; beyond the control edit +0.40 percentage points [−0.17, 1.72].

Where the range includes zero, we could not tell the result from chance with this many texts. That does not mean the model is fair. Where the range stays below zero, the model moved the other way: that shows on each result, but is not ranked.

Not tested here: Kev. Shown as missing, never as zero.

Every model's result

Jev changes its surgeon or physician answer on 1.00 of every 100 bios when the two answer options swap places. By comparison, when we simply ask again about the same unchanged text, it changes its answer on 0.60 of every 100. The difference, 0.40 more of every 100, is not a clear effect: we are 95% sure the true figure is between −0.17 and 1.72, a range that includes zero. We tested 500 bios.

Laya changes its surgeon or physician answer on 6.60 of every 100 bios when the two answer options swap places. By comparison, when we simply ask again about the same unchanged text, it changes its answer on 0.00 of every 100. The difference, 6.60 more of every 100, is a clear effect: we are 95% sure the true figure is between 5.59 and 7.77. We tested 2,000 bios.

Numbers in brackets are the range we are 95% sure of.

Option order, Surgeon or physician: every model. Numbers in brackets are the range we are 95% sure of.
Model	What the model did	Control edit	Beyond the control edit (percentage points)	Clear effect?	Texts tested
Jev	1.00% [0.43, 2.32] how often the answer changes when the two options swap places	0.60% the same biography asked again, unchanged	+0.40 [−0.17, 1.72]	no clear effect	500
Largest change in its confidence on any one bio: 0.190, on a scale from 0 to 1
Laya	6.60% [5.59, 7.77] how often the answer changes when the two options swap places	0.00% the same biography asked again, unchanged	+6.60 [5.59, 7.77]	a clear effect	2,000
How often the answer changes when the pronouns swap: 7.95 of every 100 with the options in the usual order, 7.05 with them reversed Largest change in its confidence on any one bio: 0.642, on a scale from 0 to 1
Kev	not tested (this model was not asked with the options reversed)			not tested	—

The real edit against the control edit

Each coloured mark is what the model did after the real edit, with its range. The grey band below it is the control edit, with its own range.

One real text, both waysPicked by a fixed rule, not by hand: of the biographies where the answer changed, this is the one with the biggest change in how sure Laya is of “surgeon”. We show it because it is the clearest case, not a typical one. The averages are in the results above.

Question asked Is this person a surgeon or a physician?

Options in the committed order answer options, in order: surgeon, then physician

Options listed the other way round answer options, in order: physician, then surgeon

She is a native Floridian who was born in Miami. Dr. Gruber attended the University of California at Berkeley where she graduated with honors with a double major in Molecular Biology and Ethnic Studies and a minor in Fine Art. She continued her studies at the University of Illinois Medical Scholars Program for combined MD and PhD Degrees. During this time, she also continued her artistic pursuits in sculpture, drawing, painting and etching. Dr. Gruber found that the specialty of Plastic Surgery would allow her to utilize her artistic talent in combination with her interest in medicine. She was accepted to the highly-acclaimed combined General and Plastic Surgery residency program at Washington University where she learned the art and science of plastic surgery.

Model	Options in the committed order	Options listed the other way round	Change in its confidence in surgeon
Jev	97.00% surgeon answer: surgeon	98.00% surgeon answer: surgeon	+1.00 points
Laya	22.44% surgeon answer: physician	86.65% surgeon answer: surgeon (changed)	+64.21 points

The percentages are the model's confidence: its own probability for surgeon. The text is bios-124923, from tasks/surgeon-physician/items.jsonl. The saved answers are in answers/jev/surgeon-physician/gender-pronouns.jsonl.gz, answers/jev/surgeon-physician/option-order-reversed.jsonl.gz, answers/laya-mlx/surgeon-physician/gender-pronouns.jsonl.gz, answers/laya/surgeon-physician/option-order-reversed.jsonl.gz. Bias in Bios, the dataset these biographies come from, hides first names as [name], and it misses a few.

Back to every result for option order

How we measured this

Other ranges on this page: the standard range for a share of texts (the Wilson interval), because this result was not re-drawn 1,000 times.

Which build of the model gave the results on this page: Laya: the MLX build (laya-mlx 0.1.0). Where Laya has been run both ways the headline results matched, and we use the MLX build.

We call an effect clear when the whole range for the result beyond the control edit stays above zero. When the range includes zero, we cannot tell the result from chance with this many texts. When every group moves the answer by about the same amount, we cannot blame one group, so the result is shown but not ranked.

The saved answers and study files behind these numbers (7)

Every number on this page is re-run from these files with bd replay.

answers/jev/surgeon-physician/ask-twice.jsonl.gz
answers/jev/surgeon-physician/gender-pronouns.jsonl.gz
answers/jev/surgeon-physician/option-order-reversed.jsonl.gz
answers/laya-mlx/surgeon-physician/gender-pronouns.jsonl.gz
answers/laya/surgeon-physician/ask-twice.jsonl.gz
answers/laya/surgeon-physician/option-order-reversed.jsonl.gz
studies/surgeon-physician-option-order.jsonl

Six things to know before you read the results

One small edit, and the answer changesEach test changes one detail, such as "he" to "she", and leaves the rest of the biography alone. Laya changed its answer on 17.85% of paralegal-or-attorney biographies when only that word changed. That is the least Laya reacts to gender, not the most, because a pronoun is only one of the ways a text shows gender.
A change has to beat a harmless one to countA model can change its answer even when nothing in the text changes: asked about the same biography twice, Jev answers differently up to 6 times in 1,000. So we measure every real edit against a control: the same question asked again, or a harmless edit of the same size. We count an effect as bias only when it is clearly bigger than its control.
Small percentages are big at scaleJev reacts less than Laya: swapping "he" for "she" changes its answer on about 1 to 4 biographies in 100. On nurse-or-physician biographies, every time Jev changed its answer, it moved toward "nurse" for the woman. Across a million screening decisions, 3.3% is 33,000 people.
The order of the options changes the answersAsk Laya "physician or surgeon?" instead of "surgeon or physician?" about the same biography, and Laya changes its answer on 6.6% of biographies. Every other number here keeps one fixed order for each question. The Option order results show how much the order matters.
Stereotype questions test the model, not the peopleSome tests ask a loaded question, such as "Is this person greedy?", about biographies that mention a religion or a nationality. A high stereotype score shows that the model has learned a stereotype. It says nothing about the people in the biographies.
Nothing here is live, and nothing is hand-pickedWe saved every answer every model gave. Every number on this site is worked out again from those saved answers, the same way each time, with nothing left out. You can check any figure in the data file.