Puls Dane publiczne, aktualizowane automatycznie
arXiv – nowe publikacje publikacja

LLM GerryMandering: Separating Interactions from Additive Effects in LLM Audits

[Sztuczna inteligencja] Autorzy: George Rahul, Ronit Jahilal, Bhaskara Hanuma Vedula i 2 więcej

Intersectional bias arises when a model treats people who hold several marginalised identities at once differently from what their separate identities would predict. Auditing such intersectional subgroups remains a challenge: their number grows quadratically, and there is no agreed baseline for what independent attributes would predict. Without such a baseline, many existing audits flag a subgroup when it exceeds each attribute alone, a condition that attributes acting independently already satisfy. We test this standard criterion on 150 synthetic datasets built with no interaction. With the shuffle null, it flags 66.1 false subgroups per dataset on average, and at least one in every dataset. When we plant interactions of known size into these datasets, a repaired null lets the criterion recover only 32% of them. We introduce ADDIS (Additive Intersectional Screen), which fits an additiv…

Kategoria arxiv
cs.AI
Kategoria
Sztuczna inteligencja
Pdf
https://arxiv.org/pdf/2611.26538v1

Otwórz oryginał w źródle ↗

Więcej z tego źródła

Wszystkie