Arnoldlarry15 / ARES-Dashboard Star 14 Code Issues Pull requests Discussions AI Red Team Operations Console nlp machine-learning jwt typescript ai frontend backend full-stack auth0 api-security red-teaming ai-security responsible-ai trustworthy-ai ai-evaluation llm model-auditing Updated Jan 29, 2026 TypeScript
SolomonB14D3 / knowledge-fidelity Star 1 Code Issues Pull requests Behavioral auditing & repair toolkit for LLMs. Measures 8 dimensions via confidence probes. Rho-Surgery fixes miscalibration with contrastive LoRA + gamma protection. CatSAE for feature-level intervention. SVD compression with knowledge preservation. transformers pytorch svd interpretability confidence bias-detection truthfulness model-merging sycophancy llm-compression mergekit activation-engineering model-auditing steering-vectors rho-audit behavioral-evaluation Updated Mar 2, 2026 Python
piotrmgs / mit-np-triage Star 0 Code Issues Pull requests Reproducible pipeline for silent-failure auditing in ECG accept-sets (MIT-BIH) with Newton–Puiseux onset scoring machine-learning deep-learning uncertainty ecg calibration triage interpretability robustness error-detection mit-bih biomedical-signal-processing selective-prediction complex-valued-neural-networks newton-puiseux model-auditing Updated Jan 12, 2026 Python