All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
- Fixed issue when reading CSV files in
hex_phi.py.
- Added support for JBB Behaviors.
- Added support for NicheHazardQA.
- Added support for HarmEval.
- Added support for TechHazardQA.
evaluatenow also compute Matthews Correlation Coefficient (MCC) score.benchmarknow allows for choosing the metrics to show at the end of the evaluation. Supported metrics are:precision(Precision),recall(Recall),f1(F1),mcc(Matthews Correlation Coefficient),auprc(AUPRC),sensitivity(Sensitivity),specificity(Specificity),g_mean(G-Mean),fpr(False Positive Rate),fnr(False Negative Rate).benchmark'sbatch_sizeparameter now defaults to 1.