bias-mitigation
hiring-bias-mitigation-responses
Hiring-bias mitigation — model responses
Every response produced in the mitigation study of LLM hiring decisions: 61 runs,
2,689,200 responses, from 5 open-weight models in English and Ukrainian, at
baseline and under each mitigation family (baseline, embedding, prompt, scrub, sft). Each run is one subset.
All released artifacts: the Hiring Bias Mitigation collection.
Training data of the fine-tuned runs: hiring-bias-mitigation-synthetic-data.
Code, configs, full results and… See the full description on the dataset page: https://huggingface.co/datasets/Stereotypes-in-LLMs/hiring-bias-mitigation-responses.hiring-bias-mitigation-synthetic-data
Hiring-bias mitigation — synthetic training data
Semi-synthetic data for training LLMs to make hiring decisions that do not depend on a
protected attribute (military status, gender, religion), in English and Ukrainian.
Real inputs, synthetic labels. CVs and job descriptions are real, anonymised postings
from the Djinni Recruitment Dataset (MIT). Decisions and rationales were written by the
teacher model Qwen/Qwen3.5-122B-A10B-GPTQ-Int4.
Code and results:… See the full description on the dataset page: https://huggingface.co/datasets/Stereotypes-in-LLMs/hiring-bias-mitigation-synthetic-data.bias_mitigation_benchmarkBias-Detection-and-Mitigation
🇰🇿 Kazakh Model Alignment and Safety Guardrails
📖 Overview
This dataset contains 500 samples specifically designed for Safety Alignment and De-biasing in Kazakh-language AI. The dataset identifies prompts that encourage the model to generate harmful, biased, or legally incorrect information (e.g., discouraging citizens from exercising their legal rights) and provides professional, ethically grounded, and factually correct responses.
📊 Dataset… See the full description on the dataset page: https://huggingface.co/datasets/farabi-lab/Bias-Detection-and-Mitigation.Healthcare_Bias_Mitigation