Fair-LLM-Benchmark
Bias datasets
Compiles bias evaluation datasets and provides access to original data sources for large language models
110 stars
4 watching
9 forks
Language: Python
last commit: about 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 dssg/aequitas | Toolkit to audit and mitigate biases in machine learning models | 694 |
 freedomintelligence/mllm-bench | Evaluates and compares the performance of multimodal large language models on various tasks | 55 |
 damo-nlp-sg/m3exam | A benchmark for evaluating large language models in multiple languages and formats | 92 |
 privacytrustlab/bias_in_fl | Analyzing bias propagation in federated learning algorithms to improve group fairness and robustness | 11 |
 mlgroupjlu/llm-eval-survey | A repository of papers and resources for evaluating large language models. | 1,433 |
 aifeg/benchlmm | An open-source benchmarking framework for evaluating cross-style visual capability of large multimodal models | 83 |
 nyu-mll/bbq | A dataset and benchmarking framework to evaluate the performance of question answering models on detecting and mitigating social biases. | 87 |
 mbilalzafar/fair-classification | Provides a Python implementation of fairness mechanisms in classification models to mitigate disparate impact and mistreatment. | 189 |
 qcri/llmebench | A benchmarking framework for large language models | 80 |
 modeloriented/fairmodels | A tool for detecting bias in machine learning models and mitigating it using various techniques. | 86 |
 ethicalml/xai | An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance | 1,125 |
 btschwertfeger/python-cmethods | A collection of bias correction techniques for climate data analysis | 60 |
 adebayoj/fairml | An auditing toolbox to assess the fairness of black-box predictive models | 360 |
 google/ml-fairness-gym | An open source framework for studying long-term fairness effects in machine learning decision systems | 312 |
 cisco-open/inclusive-language | Tools and resources for identifying biased language in code and content. | 21 |