Tag: explainable AI

A new open-access framework combines graph neural networks, LSTM models, large language models and federated learning to detect money laundering ...

A new multimodal AI system called HMTF-Net combines text, conversation context, user interaction graphs, images and metadata to detect cyberbullying, ...

SalientNet is an unsupervised framework that generates mechanistically grounded saliency maps for CNN medical image classifiers, outperforming Grad-CAM, Grad-CAM++, and ...

An explainable XGBoost model retained good discrimination for 28-day mortality in a later MIMIC-IV calendar period, but early hemodynamic summaries ...

Researchers report a multimodal framework combining Bengali OCR, hybrid visual encoders, and vision-language reasoning that achieved 97% accuracy on a ...

A benchmark study couples CNN saliency maps, a cortical atlas and three LLMs to generate interpretable diagnostic reports from brain ...

A PRISMA-based systematic review of 119 studies from 2018 to 2026 maps AI and robotics applications across industries, alongside challenges ...

Researchers combined a conditional diffusion model, a hypertuned YOLO26x detector and a Swin-V2-B classifier with a new SHAP-CAM explainability method ...

A systematic review of mortgage-lending fairness research finds decision trees offer the most interpretable bias detection while neural networks and ...

A study using SHAP-based explainable AI finds that US size-sorted ESG portfolios track their size benchmarks, with small-cap ESG portfolios ...