14 datasets found

The dataset used in the paper is not explicitly described, but it is mentioned that it is a dataset for Explainable Computational Creativity (XCC) systems.

ChartCheck is a novel, large-scale dataset for explainable fact-checking against real-world charts, consisting of 1.7k charts and 10.5k human-written claims and explanations.

Semantically Rich Local Dataset Generation for Explainable AI in Genomics

SYNGOALEX is a collection of 1024 text samples conditioned on three dimensions: topics, writing styles, and languages.

OPENGOALEX is a collection of 12 open-ended GOALEX problems.

The proposed interpretable CADx framework is devised to provide the diagnostic decision with interpretation in terms of medical descriptions (BI-RADS).

The HateXplain dataset, containing 20,000 posts from Gab and Twitter, annotated with hate/offensive/normal labels.

ERASER is a benchmark for evaluating rationales on NLP models.

ferret is a Python library to simplify the use and comparisons of XAI methods on transformer-based classifiers.

Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating...

Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics.

The paper introduces a new version of ALIME, which uses a decision tree instead of a linear model as the locally interpretable model.

Automatic Concept Embedding Model (ACEM) is a model that learns concept annotations automatically, without requiring concept annotations for all training data.

Explainable AI for AML genetic subtype classification