Julian Skirzynski
@jskirzynski.bsky.social
PhD student in Computer Science @UCSD. Studying interpretable AI and RL to improve people's decision-making.
Despite their unreliability, explanations are suggested as anti-discrimination measures by a number of regulations.
GDPR ✓ Digital Services Act ✓ Algorithmic Accountability Act ✓ GDPD (Brazil) ✓
GDPR ✓ Digital Services Act ✓ Algorithmic Accountability Act ✓ GDPD (Brazil) ✓
June 24, 2025 at 6:14 AM
Despite their unreliability, explanations are suggested as anti-discrimination measures by a number of regulations.
GDPR ✓ Digital Services Act ✓ Algorithmic Accountability Act ✓ GDPD (Brazil) ✓
GDPR ✓ Digital Services Act ✓ Algorithmic Accountability Act ✓ GDPD (Brazil) ✓
BADLY.
When participants flag discrimination, they are correct ~50% of the time, miss 55% of the discriminatory predictions and keep a 30% FPR.
Additional knowledge (protected attributes, proxy strength) improves the detection to roughly 60% without affecting other measures.
When participants flag discrimination, they are correct ~50% of the time, miss 55% of the discriminatory predictions and keep a 30% FPR.
Additional knowledge (protected attributes, proxy strength) improves the detection to roughly 60% without affecting other measures.
June 24, 2025 at 6:14 AM
BADLY.
When participants flag discrimination, they are correct ~50% of the time, miss 55% of the discriminatory predictions and keep a 30% FPR.
Additional knowledge (protected attributes, proxy strength) improves the detection to roughly 60% without affecting other measures.
When participants flag discrimination, they are correct ~50% of the time, miss 55% of the discriminatory predictions and keep a 30% FPR.
Additional knowledge (protected attributes, proxy strength) improves the detection to roughly 60% without affecting other measures.
We recruited participants, anchored their beliefs on discrimination, trained them to use explanations, and tested to make sure they got it right.
We then saw how well they could flag unfair predictions based on counterfactual explanations and feature attribution scores.
We then saw how well they could flag unfair predictions based on counterfactual explanations and feature attribution scores.
June 24, 2025 at 6:14 AM
We recruited participants, anchored their beliefs on discrimination, trained them to use explanations, and tested to make sure they got it right.
We then saw how well they could flag unfair predictions based on counterfactual explanations and feature attribution scores.
We then saw how well they could flag unfair predictions based on counterfactual explanations and feature attribution scores.
Participants audit a model to predict if robots sent to Mars will break down. Some are built by “Company X.” Others by “Company S.”
Our model predicts failure based on robot body parts. It can discriminate against Company X by predicting that robots without an antenna fail.
Our model predicts failure based on robot body parts. It can discriminate against Company X by predicting that robots without an antenna fail.
June 24, 2025 at 6:14 AM
Participants audit a model to predict if robots sent to Mars will break down. Some are built by “Company X.” Others by “Company S.”
Our model predicts failure based on robot body parts. It can discriminate against Company X by predicting that robots without an antenna fail.
Our model predicts failure based on robot body parts. It can discriminate against Company X by predicting that robots without an antenna fail.
Imagine a model that predicts loan approval based on credit history and salary.
Would a rejected female applicant get approved if she somehow applied as a man?
If yes, her prediction was discriminatory.
Fairness requires predictions to stay the same regardless of the protected class.
Would a rejected female applicant get approved if she somehow applied as a man?
If yes, her prediction was discriminatory.
Fairness requires predictions to stay the same regardless of the protected class.
June 24, 2025 at 6:14 AM
Imagine a model that predicts loan approval based on credit history and salary.
Would a rejected female applicant get approved if she somehow applied as a man?
If yes, her prediction was discriminatory.
Fairness requires predictions to stay the same regardless of the protected class.
Would a rejected female applicant get approved if she somehow applied as a man?
If yes, her prediction was discriminatory.
Fairness requires predictions to stay the same regardless of the protected class.
Right to explanation laws assume explanations help people detect algorithmic discrimination.
But is there any evidence for that?
In our latest work w/ David Danks @berkustun, we show explanations fail to help people, even under optimal conditions.
PDF shorturl.at/yaRua
But is there any evidence for that?
In our latest work w/ David Danks @berkustun, we show explanations fail to help people, even under optimal conditions.
PDF shorturl.at/yaRua
June 24, 2025 at 6:14 AM
Right to explanation laws assume explanations help people detect algorithmic discrimination.
But is there any evidence for that?
In our latest work w/ David Danks @berkustun, we show explanations fail to help people, even under optimal conditions.
PDF shorturl.at/yaRua
But is there any evidence for that?
In our latest work w/ David Danks @berkustun, we show explanations fail to help people, even under optimal conditions.
PDF shorturl.at/yaRua