debias 开源项目推荐（13 个）

tangxyw /RecSysPapers

推荐/广告/搜索领域工业世界经典及最前沿论坛综合。推荐/广告/搜索领域的行业经典和前沿论文集。

tolga-b /debiaswe

Remove problematic gender bias from word embeddings.

yanxinzju /CSS-VQA

Counterfactual Samples Synthesizing for Robust VQA

Yanghao-Wang /RandBox

[ICCV 2023] PyTorch implementation of RandBox

HenryPengZou /JointMatch

[EMNLP 2023] Official Code of "JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification"

sunipa /On-Measuring-and-Mitigating-Biased-Inferences-of-Word-Embeddings

Debiasing both contextual and context free embeddings and developing a downstream metric for bias measurement

aahmadnejad /BiasCXR

This repository is a debiassing project on CXR Dataset with embedding which is publicly available.

HenryPengZou /DeCrisisMB

[EMNLP 2023] Official Code of "DeCrisisMB: Debiased Semi-Supervised Learning for Crisis Tweet Classification via Memory Bank"

dhingratul /Sequence-Models

Course 5 from deeplearning.ai

PrithivirajDamodaran /bias-bench

Extension of bias-bench for select Sentence Transformers* models

zhounan111maker /dml-target-leakage-diagnosis

A controlled negative-result diagnostic study: how a single derived feature leaked the outcome Y(0) into DML covariates, appearing to cut ATE error by 89.8% while collapsing estimator variance 4x.

jpeckenpaugh /nexttext

nexttext is a lightweight Python toolkit for neutralizing explicit gendered terms in text. Via simple, fast heuristics it helps clean and standardize AI-generated labels, reducing model-induced misgendering and other unwanted linguistic artifacts. It's intended for use in AI pipelines, for both processing training data or filtering model outputs.

KiraKC /equal.txt

Identifying gender bias in film reviews through three distinct Natural Language Processing models