Skip to main content

Historical bias

A source of harm in which the training data accurately records a world that was already unjust, so a correctly built model faithfully reproduces the injustice. There is no data defect to repair; the fix is a governance decision about the objective or about whether to automate the decision at all.

Defined in 2 GAGE programs, which carry 3 distinct definitions of it. The wording above is taught in AI Governance: Applied Mastery.

How each discipline defines it

The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.

AI Governance: Applied Mastery

A source of harm in which the training data accurately records a world that was already unjust, so a correctly built model faithfully reproduces the injustice. There is no data defect to repair; the fix is a governance decision about the objective or about whether to automate the decision at all.

AI Literacy & Professional Conduct

Bias entering because the training data accurately records a past that was unfair, even when the data is complete and correct (Suresh and Guttag, 2021).

AI Literacy & Professional Conduct

A skew that arises when data accurately records an unfair real world, so the AI learns the unfairness as a pattern; not caught by accuracy checks.

Where it is taught

The exact lessons this term appears in. The first 7 topics of every program are free with a free account.

Terms it appears with

Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.