[TrustNLP@NAACL 2025] BiasEdit: Debiasing Stereotyped Language Models via Model Editing

Tools and resources of the paper "Do Neural Ranking Models Intensify Gender Bias?"

Scientific Data Significance Rankings with Shapley Explanations

A game about diversity

This project aims to investigate different models for solving the stereotype detection task.

INFORMATIK22: Measuring Gender Bias in German Language Generation

Some scripts for evaluating stereotypes in LMs

Investigating how culturally sensitive terms are used in Linked Open Data

CalgaryHacks 2021 :: Rogue-like adventure game heavily based on widespread Canadian stereotypes.

This repository contains the code of the team StereoBusters for the Evalita 2026 task GSI-detect: Detecting Gender Stereotypes in Italian

This study investigates social biases in text-to-image models by examining biases in AI-generated images across demographic, occupational, and cultural prompts. Testing diverse inputs and collecting feedback, we aim to identify and analyze biases to propose strategies for fairer, more inclusive AI-generated visuals.

🔍 Analyze datasets with DataTypical to identify key instances and their impact, using Shapley explanations for clear insights into data structure.