Biasing Rule-Based Explanations Towards User Preferences
With the growing prevalence of Explainable AI (XAI), the effectiveness, transparency, usefulness, and trustworthiness of explanations have come into focus. However, recent work in XAI often still falls short in terms of integrating human knowledge and preferences into the explanatory process. In thi...
Saved in:
| Main Authors: | Parisa Mahya, Johannes Fürnkranz |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/7/535 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
An Empirical Comparison of Interpretable Models to Post-Hoc Explanations
by: Parisa Mahya, et al.
Published: (2023-05-01) -
Local Universal Rule-based eXplainer (LUX)
by: Szymon Bobek, et al.
Published: (2025-05-01) -
A Study Comparing Explainability Methods: A Medical User Perspective
by: Matejová Miroslava, et al.
Published: (2025-06-01) -
Interpretarea, instrument de atenuare a bias-ului algoritmic în contractele electronice/ Interpretation, a Tool for Mitigating Algorithmic Bias in Electronic Contracts
by: Sebastian ANTOCE
Published: (2025-07-01) -
XAI Unveiled: Revealing the Potential of Explainable AI in Medicine: A Systematic Review
by: Noemi Scarpato, et al.
Published: (2024-01-01)