Apps

🧪 This platform is in early beta. Features may change and you might encounter bugs. We appreciate your patience!

Racial Stereotyping

Also Known As: Racial Profiling (behavioral) Ethnic Stereotyping Racial Generalization
Manipulation & Propaganda 🎯 Discrimination Detection ID: racial_stereotyping

Definition

Racial stereotyping assigns fixed traits, abilities, or behaviors to all members of a racial or ethnic group. It operates on a spectrum from overt slurs and explicit claims of racial superiority to subtle assumptions embedded in everyday language — such as expressing surprise at someone's eloquence based on their race. Context matters: the same observation can be descriptive in one setting and stereotyping in another. The pattern becomes problematic when individual characteristics are attributed to group membership rather than personal context.

Examples

A news anchor states: 'Asian students consistently outperform others in math — it's simply part of their culture.' While framed as a compliment, this assigns a fixed trait to an entire racial group.

A politician argues: 'We need tougher policing in those neighborhoods — everyone knows certain communities have higher crime rates.' This links criminality to race rather than examining socioeconomic factors.

A colleague says: 'You're so articulate!' to a Black professional, expressing surprise that implicitly assumes lower linguistic competence as the baseline for that racial group.

Formal Logic Pattern
FOL Pattern
The First-Order Logic formula representing this reasoning pattern's logical structure.
FOL (First-Order Logic) uses quantifiers (∀ = for all, ∃ = there exists), connectives (∧ = and, ∨ = or, ⇒ = implies, ¬ = not), and predicates to capture the essential form of a reasoning pattern. For example, the Ad Hominem fallacy: Person(x) ∧ HasFlaw(x) ⇒ Invalid(Claim(x)). These patterns allow automated verification of logical validity.

∃g∃p(Group(g) ∧ Racial(g) ∧ Property(p) ∧ ∀x(Member(x,g) → HasProperty(x,p)) ∧ ¬Justified(∀x(Member(x,g) → HasProperty(x,p))))
Formal Verification:
Formal Verification
Checks whether a reasoning pattern is logically valid or invalid using an automated theorem prover.
Formal verification uses an SMT (Satisfiability Modulo Theories) solver — specifically Z3 — to mathematically check whether an argument's logical structure is valid. Each reasoning pattern is translated into First-Order Logic and tested: Can the premises be true while the conclusion is false? If yes, it's formally invalid. If no, it's formally valid. Many real-world patterns (analogies, heuristics) cannot be fully captured in formal logic — these are marked as not formally decidable, which doesn't mean they're wrong.
Not formally decidable

Verification Steps
Verification Steps
Binary yes/no questions that an AI must answer to detect a reasoning pattern in a text.
Each of the 452 aspects has verification steps — simple yes/no questions designed to systematically detect whether a pattern appears in a text. For ad hominem: "Does the argument attack a person rather than their claim?" For false dichotomy: "Are only two options presented when more exist?" This ensures consistent, reproducible analysis.

Binary (yes/no) questions an LLM must answer to identify this aspect:

  1. 1

    Does the statement attribute characteristics to an entire racial or ethnic group?

    Type: binary
  2. 2

    Are these attributes presented as inherent rather than contextual?

    Type: binary
  3. 3

    Does the statement ignore individual variation within the group?

    Type: binary
  4. 4

    Could the generalization lead to prejudicial treatment or perception?

    Type: binary
Deep Dive
The expandable detail section on each aspect page with examples, psychology, and counter-strategies.
The Deep Dive section provides in-depth information about each aspect: a real-world example showing the pattern in action, an explanation of why it works psychologically, practical advice on how to counter it, alternative names, and links to related aspects.