paper-with-me

홈 › Papers

Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction

2022-10-19 · José Ribeiro, Níkolas Carneiro, Ronnie Alves

Strategies based on Explainable Artificial Intelligence (XAI) have promoted better human interpretability of the results of black box models. This opens up the possibility of questioning whether explanations created by XAI methods meet human expectations. The XAI methods being currently used (Ciu, Dalex, Eli5, Lofo, Shap, and Skater) provide various forms of explanations, including global rankings of relevance of features, which allow for an overview of how the model is explained as a result of its inputs and outputs. These methods provide for an increase in the explainability of the model and a greater interpretability grounded on the context of the problem. Intending to shed light on the explanations generated by XAI methods and their interpretations, this research addresses a real-world classification problem related to homicide prediction, already peer-validated, replicated its proposed black box model and used 6 different XAI methods to generate explanations and 6 different human experts. The results were generated through calculations of correlations, comparative analysis and identification of relationships between all ranks of features produced. It was found that even though it is a model that is difficult to explain, 75\% of the expectations of human experts were met, with approximately 48\% agreement between results from XAI methods and human experts. The results allow for answering questions such as: "Are the Expectation of Interpretation generated among different human experts similar?", "Do the different XAI methods generate similar explanations for the proposed problem?", "Can explanations generated by XAI methods meet human expectation of Interpretations?", and "Can Explanations and Expectations of Interpretation work together?".

📄 PDF Abstract BibTeX arXiv:2210.10849

Code (2)

josesousaribeiro/conexi 공식 구현
josesousaribeiro/pred2town-and-xai 공식 구현

Tasks

AttributeExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Similar Papers 제목 키워드 기반

Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection

2022-05-01 · nlppower (ACL) 2022 5 · Giuseppe Attanasio, Debora Nozza, Eliana Pastor, Dirk Hovy

Transformer-based Natural Language Processing models have become the standard for hate speech detection. However, the unconscious use of these techniques for such a critical task comes with negative consequences. Various…

BenchmarkingHate Speech Detection

One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency

2020-01-27 · Kacper Sokol, Peter Flach

The need for transparency of predictive systems based on Machine Learning algorithms arises as a consequence of their ever-increasing proliferation in the industry. Whenever black-box algorithmic predictions influence hu…

AllBIG-bench Machine LearningcounterfactualInterpretable Machine Learning

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

2024-10-29 · Shaobo Wang, Hongxuan Tang, Mingyang Wang, Hongrui Zhang 외

The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting deci…

Computational Efficiency

Thermodynamics-inspired Explanations of Artificial Intelligence

2022-06-27 · Shams Mehdi, Pratyush Tiwary

In recent years, predictive machine learning methods have gained prominence in various scientific domains. However, due to their black-box nature, it is essential to establish trust in these models before accepting them …

feature selectionimage-classificationImage Classificationtext-classification+1

AcME -- Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Box

2021-12-23 · David Dandolo, Chiara Masiero, Mattia Carletti, Davide Dalle Pezze 외

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability approaches should provide actionable insights without making the users wait. In this paper, we propose Ac…

BIG-bench Machine LearningFeature Importance