Bias Detection Transformers Transformer Models

Tools for detecting, measuring, and mitigating biases (social, textual, visual, linguistic) in transformer models and NLP systems. Does NOT include general model interpretability, fairness frameworks without bias focus, or robustness testing unrelated to bias.

There are 18 bias detection transformers models tracked. The highest-rated is zalkikar/mlm-bias at 43/100 with 4 stars.

Get all 18 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=bias-detection-transformers&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Model	Score	Tier	Stars	Language
1	zalkikar/mlm-bias Measuring Biases in Masked Language Models for PyTorch Transformers. Support...	43	Emerging	4	Python
2	ejurasek00/Hashing_LLM_Debiasing Repository consisting of the files used in the experiments + brief...	32	Emerging	1	Python
3	koudounasalkis/CLUES This repo contains the code for "A Contrastive Learning Approach to Mitigate...	31	Emerging	3	Python
4	anoopkdcs/NLPBias Towards Comprehensive Understanding of Bias in Pre-trained Neural Language...	23	Experimental	4	—
5	shikhartuli/cnn_txf_bias [CogSci'21] Study of human inductive biases in CNNs and Transformers.	23	Experimental	43	Jupyter Notebook
6	gdorleon/mbib-framing-crf Code (CRF + Transformers) to reproduce the experiments from the paper...	22	Experimental	1	Python
7	edsonpro9891/robust-nli-analysis 🔍 Detect biases in NLP models with robust analysis, enhancing dataset...	21	Experimental	—	Python
8	JuaniLlaberia/news-bias-detection-research Random splits let bias detection models memorize publishers instead of...	21	Experimental	—	Jupyter Notebook
9	CaterinaBi/health-communication-paper2 Bonan & Samo. January 2023. Paper on cross-linguistic bias in health-related...	21	Experimental	1	TeX
10	codewithdark-git/Bias Steer Language Models with Interpretable SAE Features	20	Experimental	1	Python
11	koudounasalkis/divergence-in-speech-systems Code associated with the paper "Exploring Subgroup Performance in End-to-End...	20	Experimental	6	Jupyter Notebook
12	Aqib121201/FairNLP-SHAP-Based-Bias-Detection-in-Multilingual-BERT-Models Bias analysis in multilingual BERT using SHAP and fairness metrics (EN, DE, HI)	20	Experimental	3	Python
13	koudounasalkis/Data-Acquisition-for-Speech-Model-Improvement This repo contains the code for "Prioritizing Data Acquisition For...	19	Experimental	3	Jupyter Notebook
14	koudounasalkis/Subgroup-Analysis-in-Speech-Models This repo contains the code for "Towards Comprehensive Subgroup Performance...	19	Experimental	3	Jupyter Notebook
15	argrecsys/arg-min-fw Welcome to the Framework for Mining Arguments repository! This project aims...	17	Experimental	1	Python
16	OliverStoll/texture-bias-analysis "On the Prevalence of Texture Bias in Deep Learning Models for Remote...	13	Experimental	—	Python
17	ngi-indi/module-bias-manager Flask application for bias detection and explanation in Web content.	11	Experimental	—	Python
18	eric11eca/saint-nli A new evaluation mechanism and a learning strategy for de-biased and...	11	Experimental	—	Jupyter Notebook