explainable AI
PulseAugur coverage of explainable AI — every cluster mentioning explainable AI across labs, papers, and developer communities, ranked by signal.
15 day(s) with sentiment data
-
New BREAD method enhances AI anomaly diagnosis accuracy
Researchers have developed a new method called BREAD (Baseline-Referenced Explanations for Anomaly Diagnosis) to improve the accuracy of identifying features that cause anomalies in artificial intelligence systems. This…
-
Study: XAI explanation correctness impacts human understanding, but not always
A new study published on arXiv investigates the relationship between the functional correctness of explainable AI (XAI) methods and human understanding. Researchers conducted a user study with 200 participants, manipula…
-
New XAI method enhances transparency in remote sensing image segmentation
A new method for explainable AI (XAI) has been developed to improve the transparency of AI models used in remote sensing image segmentation. This entropy-centric approach aims to provide insights into the decision-makin…
-
New framework enhances IoMT security with AI and privacy preservation
A new framework has been proposed to enhance the security and privacy of Internet of Medical Things (IoMT) systems. This framework utilizes Artificial Neural Networks for intrusion detection and incorporates Federated L…
-
Conversational AI boosts UAV intrusion detection usability but risks over-reliance
A new study published on arXiv explores the effectiveness of conversational explainable AI (XAI) interfaces compared to traditional dashboard-based XAI for Unmanned Aerial Vehicle (UAV) intrusion detection systems. Rese…
-
New framework uses LLMs to select explainable AI for TinyML edge devices
Researchers have developed a new framework for selecting explainable AI (XAI) methods for TinyML edge devices, particularly for clinical applications. This framework uses a large language model (LLM) to guide the design…
-
20 Generative AI Concepts for 2026 Explained
This article provides a plain-English guide to 20 key generative AI concepts relevant for 2026. It covers foundational ideas such as large-language models, transformers, and prompt engineering, alongside more advanced t…
-
Paper highlights challenges in evaluating AI explanation methods
This paper examines the shortcomings in evaluating Explainable Artificial Intelligence (XAI) methods, particularly when dealing with static and evolving data. It illustrates these challenges using the DetoxAI system for…
-
New 'Neural Echo' Framework Bridges Signal Processing and Explainable AI
Researchers have introduced a new framework called the "neural echo" to better understand the internal workings of neural networks. This method generalizes concepts from classical signal processing, such as impulse resp…
-
AI enhances rip current detection using UAVs and wavelet texture analysis
Researchers have developed a new method for monitoring rip currents using unmanned aerial vehicles (UAVs) by integrating wavelet-derived texture features with deep learning. This approach enhances the detection of subtl…
-
New AI framework enhances archaeological sensing data quality
Researchers have developed a multimodal machine-learning framework designed to improve the calibration and quality assessment of archaeological sensing workflows. This framework integrates various data types from photog…
-
New EPC Score Validates AI Explainability Against Human Judgment
Researchers have developed a new metric called the Explainability-Performance Coefficient (EPC) score to better evaluate the quality of explanations provided by artificial intelligence systems. This model-agnostic metri…
-
JobMatchAI platform uses knowledge graphs and explainable AI for better job matching
A new research paper introduces JobMatchAI, a job matching platform designed to improve upon traditional keyword-based search systems. This platform integrates Transformer embeddings, skill knowledge graphs, and explain…
-
Explainable AI achieves 99% accuracy in Chronic Kidney Disease prediction
Researchers have developed an explainable AI (XAI) model using simulated federated learning to predict Chronic Kidney Disease (CKD). The model, which integrates Random Forest, AdaBoost, and XGBoost algorithms, achieved …
-
Explainable AI impacts developer trust and agreement in code reviews
A new study published on arXiv explores how Explainable AI (XAI) influences developer trust in AI-assisted code reviews. The research found that while full explanations led to higher perceived trust, they did not necess…
-
New AI framework enhances transparency in flood prediction models
Researchers have developed a new framework called Context-Aware Concept Distillation (CACD) to make deep learning models more transparent for flood prediction. This approach distills complex LSTM models into interpretab…
-
New XAI approach lets artists interactively bend diffusion models
Researchers have developed a new approach to explainable AI (XAI) specifically for artists working with text-to-image diffusion models. This method focuses on enabling artists to interactively inspect, modify, and debug…
-
New benchmark library standardizes evaluation of explainable AI methods
Researchers have introduced CEL, a Comprehensive Counterfactual Explanations Library and Benchmark, to address the challenges in evaluating explainable AI (xAI) methods. Existing studies often lack consistency in data s…
-
New XAI method verifies ML decisions in optical networks
Researchers have developed a new method called explanation-based runtime verification to enhance the trustworthiness of machine learning models used in optical networks. This approach leverages explainable AI (XAI) tech…
-
New LLIFT framework generates realistic medical images for AI validation
Researchers have developed a new framework called Local Label-Informed Feature Transfer (LLIFT) to generate semi-synthetic brain MRI images with realistic lesions. This method aims to create more reliable ground-truth d…