SOTAVerified

Explainable artificial intelligence

XAI refers to methods and techniques in the application of artificial intelligence (AI) such that the results of the solution can be understood by humans. It contrasts with the concept of the "black box" in machine learning where even its designers cannot explain why an AI arrived at a specific decision. XAI may be an implementation of the social right to explanation. XAI is relevant even if there is no legal right or regulatory requirement—for example, XAI can improve the user experience of a product or service by helping end users trust that the AI is making good decisions. This way the aim of XAI is to explain what has been done, what is done right now, what will be done next and unveil the information the actions are based on. These characteristics make it possible (i) to confirm existing knowledge (ii) to challenge existing knowledge and (iii) to generate new assumptions.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 651–675 of 971 papers

TitleStatusHype
"Explanation" is Not a Technical Term: The Problem of Ambiguity in XAI—0
Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models—0
Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability—0
Visualizing and Understanding Contrastive LearningCode0
Eliminating The Impossible, Whatever Remains Must Be TrueCode0
Machine Learning in Sports: A Case Study on Using Explainable Models for Predicting Outcomes of Volleyball Matches—0
Towards ML Methods for Biodiversity: A Novel Wild Bee Dataset and Evaluations of XAI Methods for ML-Assisted Rare Species AnnotationsCode1
Attributions Beyond Neural Networks: The Linear Program Case—0
Explainable expected goal models for performance analysis in football analyticsCode0
Mediators: Conversational Agents Explaining NLP Model Behavior—0
Xplique: A Deep Learning Explainability ToolboxCode2
ECLAD: Extracting Concepts with Local Aggregated Descriptors—0
Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models—0
Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey—0
From Attribution Maps to Human-Understandable Explanations through Concept Relevance PropagationCode1
Predicting and Understanding Human Action Decisions during Skillful Joint-Action via Machine Learning and Explainable-AICode0
Can Requirements Engineering Support Explainable Artificial Intelligence? Towards a User-Centric Approach for Explainability Requirements—0
Comparing interpretation methods in mental state decoding analyses with deep learning models—0
Multivariate Probabilistic Forecasting of Intraday Electricity Prices using Normalizing Flows—0
TSEM: Temporally Weighted Spatiotemporal Explainable Neural Network for Multivariate Time SeriesCode0
Towards Better Understanding Attribution MethodsCode1
A Psychological Theory of Explainability—0
Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract SettingCode0
The Conflict Between Explainable and Accountable Decision-Making Algorithms—0
A Meta-Analysis of the Utility of Explainable Artificial Intelligence in Human-AI Decision-Making—0
Show:102550
← PrevPage 27 of 39Next →

No leaderboard results yet.