Topic
explainable ai
AI Model Predicts Five-Year Heart Failure Risk from 24-Hour ECG Data
Researchers at Technion and Leumit Health Services developed DeepHHF, a deep learning model that analyzes 24-hour single-lead ECG recordings to predict heart failure risk within five years. The model achieved an AUC of 0.80, outperforming shorter segments and clinical scores, and identified high-risk individuals with a twofold chance of hospitalization or death.
Explainable deep learning improves human mental models of self-driving cars, study finds
A new method called Concept-Wrapper Network (CW-Net) provides faithful explanations of deep neural network planners in self-driving cars, improving human drivers' ability to anticipate vehicle behavior, especially in surprising situations. Deployed on a real autonomous vehicle, the system shows that explainable AI can be practical and useful in real-world settings.
Reinforcement Learning with Chain-of-Thought Supervision Boosts Hateful Meme Detection Accuracy by Over 2%
A new reinforcement learning-based post-training method using Group Relative Policy Optimization and chain-of-thought supervision improves hateful and propagandistic meme detection. On the FHM benchmark, accuracy rose from 79.9% to 82.0%; on ArMeme, macro-F1 increased by 7.6 points to 0.612. The approach also generates natural-language explanations for predictions.
New DAG-SHAP Method Improves Feature Attribution Using Edge Intervention in Directed Acyclic Graphs
Researchers introduce DAG-SHAP, a feature attribution method for directed acyclic graphs that uses edge intervention to address limitations of node-centric Shapley value approaches. The method captures both externality and exogenous influence, validated on real and synthetic datasets.
RecourseBench: Modular Framework Promises Reproducible Evaluation of AI Recourse Methods
A new framework called RecourseBench aims to standardize and validate algorithmic recourse methods—counterfactual explanations that show individuals how to reverse an AI's decision. It decomposes the evaluation pipeline into five decoupled layers and integrates 28 state-of-the-art methods, with automated tests to verify reproducibility.