arXiv (All)
open access
Harm Is Behavioural, Moderation Is Lexical: How Language and Culture Decide Whom Automated Safety Systems Protect and Whom They Silence
Content warning: this paper quotes slurs and hateful statements from published test suites; the racial slur among them is masked. Automated systems decide at scale which messages are harmful, and they decide unevenly. Classifiers label African American English as offensive up to twice as often as
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Professionalism Pulse: Development and Validation of a Natural Language Processing Pipeline and Dashboard for Safety Culture Surveillance in NYC Health + Hospitals#296519
- Blacks, Cops, and the State of Nature#720731
- 18 U.S.C. § 1545 — Safe conduct violation#573954
- So What's in a Name? A Rhetorical Reading of Washington's Sexually Violent Predators Act#1020022
- Impoliteness and entertainment in the television quiz show: ‘The Weakest Link’.#169250
Record · ID 1424165
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive