ExplAIner: A Declarative Query Language for Explaining Classification Models
The XAI community has studied a wide range of queries and scores for explaining predictions of ML models. From a data management perspective, this proliferation of explanation notions calls for declarative query languages in which such notions can be specified, combined, and analyzed uniformly. In this paper, we develop such a framework for Boolean models. We first revisit FOIL, an interpretability query language for black-box models, and show that it has two fundamental limitations: it cannot express central optimality-based explanation queries, and its evaluation problem over decision trees
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorMarcelo Arenas →
ExplAIner: A Declarative Query Language for Explaining Classification Models
- Linked via arxiv authorPablo Barceló →
ExplAIner: A Declarative Query Language for Explaining Classification Models
- Linked via arxiv authorDiego Bustamante →
ExplAIner: A Declarative Query Language for Explaining Classification Models
- Linked via arxiv authorJose Caraball →
ExplAIner: A Declarative Query Language for Explaining Classification Models
- Linked via arxiv authorMaría Alejandra Schild →
ExplAIner: A Declarative Query Language for Explaining Classification Models
- Linked via arxiv authorBernardo Subercaseaux →
ExplAIner: A Declarative Query Language for Explaining Classification Models