[TrustNLP@NAACL 2025] BiasEdit: Debiasing Stereotyped Language Models via Model Editing
-
Updated
Sep 30, 2025 - Python
[TrustNLP@NAACL 2025] BiasEdit: Debiasing Stereotyped Language Models via Model Editing
Scientific Data Significance Rankings with Shapley Explanations
Some scripts for evaluating stereotypes in LMs
🔍 Analyze datasets with DataTypical to identify key instances and their impact, using Shapley explanations for clear insights into data structure.
Add a description, image, and links to the stereotypes topic page so that developers can more easily learn about it.
To associate your repository with the stereotypes topic, visit your repo's landing page and select "manage topics."