Summary of Why Do Explanations Fail? a Typology and Discussion on Failures in Xai, by Clara Bove et al.
Why do explanations fail? A typology and discussion on failures in XAI
by Clara Bove, Thibault Laugel, Marie-Jeanne Lesot, Charles Tijus, Marcin Detyniecki
First submitted to arxiv on: 22 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a holistic perspective on Explainable Artificial Intelligence (XAI), highlighting the limitations of current methods and their impact on explanation interpretation. It argues that existing approaches fail to meet expectations due to technical limitations or user misinterpretations, leading to harms. The authors propose a typological framework that distinguishes between system-specific and user-specific failures, providing insights for AI practitioners to improve XAI systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making machine learning models understandable. Right now, some people are trying to make these models explainable, but it’s not working as well as they want. Some problems have been found, and this research looks at all the different issues that are causing these problems. The authors think that understanding these limitations will help make explanations better. |
Keywords
» Artificial intelligence » Machine learning
