.png){kind=icon}
Return
Toward practical human-interpretable explanations
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-025-06852-8.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Model-agnostic feature attribution techniques are used to explain the decisions of complex machine learning (ML) models including ensemble models, and deep neural networks (DNNs). However, since complex ML models perform best when trained on low-level features, the explanations generated by these algorithms are often not interpretable or usable by humans. Recently proposed model-agnostic methods that support the generation of human-interpretable explanations are impractical because they require a fully invertible transformation function that maps the model’s input features to human-interpretable features. While some practical human-interpretable explainability methods exist (e.g., concept-based methods), they typically require direct access to the model and are not fully model-agnostic. In this paper, we introduce Latent SHAP, a model-agnostic black-box feature attribution framework that provides human-interpretable explanations without necessitating a fully invertible transformation function. We validate the fidelity of Latent SHAP ’s explanations through quantitative faithfulness assessments on two controlled datasets—a self-generated artificial dataset and the dSprites dataset. Furthermore, we showcase the practical utility of Latent SHAP in various real-world scenarios across domains such as computer vision, natural language processing, and cybersecurity. Each domain involves complex models (ensembles, DNNs, and LLMs), where invertible transformation functions are not available.
Keywords:
Explainability
XAI algorithms
Machine learning
Explainable ML
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.9
Papers:
2.7K
Citations:
3.4W
Organization
Cited Papers
"Why Should I Trust You?".png)
Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIF0
PREAI
ShareSaveAffective Video Retrieval: Violence Detection in Hollywood Movies by Large-Scale Segmental Feature ExtractionPLoS ONEOAAI
PLoS ONEIF0
OAAIShareSaveShareSaveShareSaveGenerating Focused Molecule Libraries for Drug Discovery with Recurrent Neural NetworksACS CENTRAL SCIENCEOAAI
ACS CENTRAL SCIENCEIF10.4
OAAIShareSave
View more