trends.barnas.net

method · first seen 2 Nov 2026

counterfactual identity templates

Evaluation method that instantiates identical text templates with different identity terms to isolate group-specific model behavior.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

hate speech detectionmeasurement non-invariance