Bias-Mitigation-In-LLM

The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

Crosslingual Generalization through Multitask Finetuning

A face database with a large number of high-quality attribute annotations

Climate science package for Julia

This is an open-source tool to assess and improve the trustworthiness of AI systems.

使用qlora对中文大语言模型进行微调，包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE

Oracle Guardian AI Open Source Project is a library consisting of tools to assess fairness/bias and privacy of machine learning models and data sets.

Multi-Calibration & Multi-Accuracy Boosting for R

Official code of "Discover and Mitigate Unknown Biases with Debiasing Alternate Networks" (ECCV 2022)

Examples of unfairness detection for a classification-based credit model