The BIAS Detection Framework: Bias Detection in Word Embeddings and Language Models for European Languages

Alexandre Puttick, Leander Rankwiler, Catherine Ikae, Mascha Kurpicz-Briki
7/26/2024
cs.CL

No official code found. Best implementation: BFH-AMI/BIAS (5 stars, Apache-2.0, last commit 2025-12-22).

Abstract

The project BIAS: Mitigating Diversity Biases of AI in the Labor Market is a four-year project funded by the European commission and supported by the Swiss State Secretariat for Education, Research and Innovation (SERI). As part of the project, novel bias detection methods to identify societal bias in language models and word embeddings in European languages are developed, with particular attention to linguistic and geographic particularities. This technical report describes the overall architecture and components of the BIAS Detection Framework. The code described in this technical report is available and will be updated and expanded continuously with upcoming results from the BIAS project. The details about the datasets for the different languages are described in corresponding papers at scientific venues.

View on arXivView PDF

Code Implementations(1)

BFH-AMI/BIASCommunity100%
Apache-2.0

Open-source outcomes of the Horizon Europe Project BIAS.

51May 7, 202410 months agoApache-2.0

Similar Papers

Fine-Grained Bias Detection in LLM: Enhancing detection mechanisms for nuanced biases

86% match2025

Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation

84% match2025

IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators

84% match2024

Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approach

84% match2025

Current State-of-the-Art of Bias Detection and Mitigation in Machine Translation for African and European Languages: a Review

84% match2024

A Study on Bias Detection and Classification in Natural Language Processing

83% match2024

Cite this paper

@article{puttick2024bias,
  title  = {The BIAS Detection Framework: Bias Detection in Word Embeddings and Language Models for European Languages},
  author = {Alexandre Puttick and Leander Rankwiler and Catherine Ikae and Mascha Kurpicz-Briki},
  year   = {2024},
  eprint = {2407.18689},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.18689v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.18689.svg)](https://codeofpaper.com/paper/2407.18689)

Discussion