A developer argues that explainable AI's core unresolved problem is not computing explanations but communicating them to the people who must act on them, without overstating their certainty. The piece…
A physiology-guided hybrid framework combining a convolutional neural network branch with a morphology-prior branch estimated blood pressure from photoplethysmography (PPG) with mean absolute errors o…
A multimodal deep learning framework pairing a 3D CNN encoder for T1-weighted MRI with a feedforward network for harmonized clinical and demographic data achieved its highest three-class AUC-ROC of 0.…
A new arXiv paper (2609.10792v1) tests whether transformer-based models internalize the same linguistic features as traditional feature-based classifiers in Automatic Readability Assessment across Ara…
A developer argues that SHAP and other post-hoc explainability tools cannot account for the autonomous decisions and tool calls made by agentic AI fraud-detection systems, leaving an explainability ga…
A developer has compiled a list of 20 prompts for using large language models (LLMs) in data science tasks, covering model training, hyperparameter tuning, time series forecasting, handling imbalanced…
Researchers introduced ProToMEx, a model-agnostic explainability framework that uses Probabilistic Topic Models to learn latent 'topics' representing high-level reasons for classifications, providing …
A new arXiv paper (2609.00090v1) introduces a Weight of Evidence (WoE) framework to evaluate feature importance methods (FIMs) in Explainable AI, quantifying how strongly evidence supports hypotheses …
A new article outlines three techniques for enhancing AI model interpretability—SHAP, LIME, and Integrated Gradients—applied to a customer churn model, emphasizing the EU AI Act's Article 13 requireme…
Researchers introduced actionable case-based feature importance (A-CBFI), a framework for tabular machine learning that integrates structural causal models with counterfactual recourse to target inter…
Scikit-LLM, a Python library for integrating large language models into scikit-learn workflows, demonstrates how to interpret text classification by generating embeddings from movie reviews using the …
A feasibility study on the eICU Demo dataset (2,353 ICU stays, 8.1% mortality) found that a four-step agentic pipeline produced no explanations with explicit outcome leakage, while a standalone LLM pr…
A new arXiv paper (2608.23817v1) proposes an auditing protocol that measures robustness and fidelity of post-hoc explainers like SHAP and LIME, combining them into a single Trust Score. Testing on a M…
The bias-variance tradeoff and double descent, introduced by Belkin et al. (2019), shape model complexity choices with ethical consequences in machine learning. Overfit models can reinforce societal b…
A new study from arXiv (2608.20343v1) presents a bankruptcy prediction framework using hybrid resampling and stacking ensembles with explainable AI, achieving the best minority-class detection with a …
A fraud model's decision can be fully explainable yet still wrong because the underlying data pipeline fails to capture document provenance, valuation timing, and feature timestamp policies, according…
A developer built an Explainable Causal Reinforcement Learning (XC-RL) framework for wildfire evacuation logistics, incorporating a Structural Causal Model to capture causal relationships between fire…
A multi-scale stacking ensemble for credit risk scoring reached test ROC-AUC 0.9539 and PR-AUC 0.9137 on a 32,581-application dataset, beating the best single model by Delta-AUC 0.0143, but an audit o…
A practical guide argues that churn prediction models fail unless paired with prescriptive actions, urging data teams to segment at-risk users by churn driver using SHAP or LIME, map drivers to specif…
A study using BERT, a transformer-based AI model, achieved 97.05% accuracy in multilabel classification of 14,590 Mpox research articles into topics such as outbreaks, vaccination, and epidemiology, a…