Related papers: Explanation Hacking: The perils of algorithmic recourse

Explanation Hacking: The perils of algorithmic recourse

URL: http://arxiv.org/abs/2406.11843v1
Date: Fri, 22 Mar 2024 12:49:28 GMT
Title: Explanation Hacking: The perils of algorithmic recourse
Authors: Emily Sullivan, Atoosa Kasirzadeh,
Abstract summary: We argue that recourse explanations face several conceptual pitfalls and can lead to problematic explanation hacking. As an alternative, we advocate that explanations of AI decisions should aim at understanding.
Score: 2.967024581564439
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: We argue that the trend toward providing users with feasible and actionable explanations of AI decisions, known as recourse explanations, comes with ethical downsides. Specifically, we argue that recourse explanations face several conceptual pitfalls and can lead to problematic explanation hacking, which undermines their ethical status. As an alternative, we advocate that explanations of AI decisions should aim at understanding.

Related papers

Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing [51.524108608250074]
Black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in remote sensing. We perform a systematic review to identify the key trends in the field and shed light on novel explainable AI approaches. We also give a detailed outlook on the challenges and promising research directions.
arXiv Detail & Related papers (2024-02-21T13:19:58Z)
In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making [25.18203172421461]
We argue explanations are only useful to the extent that they allow a human decision maker to verify the correctness of an AI's prediction. We also compare the objective of complementary performance with that of appropriate reliance, decomposing the latter into the notions of outcome-graded and strategy-graded reliance.
arXiv Detail & Related papers (2023-05-12T18:28:04Z)
Explainable Data-Driven Optimization: From Context to Decision and Back Again [76.84947521482631]
Data-driven optimization uses contextual information and machine learning algorithms to find solutions to decision problems with uncertain parameters. We introduce a counterfactual explanation methodology tailored to explain solutions to data-driven problems. We demonstrate our approach by explaining key problems in operations management such as inventory management and routing.
arXiv Detail & Related papers (2023-01-24T15:25:16Z)
Seamful XAI: Operationalizing Seamful Design in Explainable AI [59.89011292395202]
Mistakes in AI systems are inevitable, arising from both technical limitations and sociotechnical gaps. We propose that seamful design can foster AI explainability by revealing sociotechnical and infrastructural mismatches. We explore this process with 43 AI practitioners and real end-users.
arXiv Detail & Related papers (2022-11-12T21:54:05Z)
From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse [0.0]
We argue that recourse should be viewed as a recommendation problem, not an explanation problem. We illustrate by considering the case of diversity constraints on algorithmic recourse.
arXiv Detail & Related papers (2022-05-30T20:09:42Z)
Diagnosing AI Explanation Methods with Folk Concepts of Behavior [70.10183435379162]
We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. We use folk concepts of behavior as a framework of social attribution by the human explainee.
arXiv Detail & Related papers (2022-01-27T00:19:41Z)
Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts [12.552080951754963]
Existing and planned legislation stipulates various obligations to provide information about machine learning algorithms. Many researchers suggest using post-hoc explanation algorithms for this purpose. We show that post-hoc explanation algorithms are unsuitable to achieve the law's objectives.
arXiv Detail & Related papers (2022-01-25T13:12:02Z)
Making Things Explainable vs Explaining: Requirements and Challenges under the GDPR [2.578242050187029]
ExplanatorY AI (YAI) builds over XAI with the goal to collect and organize explainable information. We represent the problem of generating explanations for Automated Decision-Making systems (ADMs) into the identification of an appropriate path over an explanatory space.
arXiv Detail & Related papers (2021-10-02T08:48:47Z)
The Who in XAI: How AI Background Shapes Perceptions of AI Explanations [61.49776160925216]
We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. We find that (1) both groups showed unwarranted faith in numbers for different reasons and (2) each group found value in different explanations beyond their intended design.
arXiv Detail & Related papers (2021-07-28T17:32:04Z)
A general framework for scientifically inspired explanations in AI [76.48625630211943]
We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
arXiv Detail & Related papers (2020-03-02T10:32:21Z)
Algorithmic Recourse: from Counterfactual Explanations to Interventions [16.9979815165902]
We argue that counterfactual explanations inform an individual where they need to get to, but not how to get there. Instead, we propose a shift of paradigm from recourse via nearest counterfactual explanations to recourse through minimal interventions.
arXiv Detail & Related papers (2020-02-14T22:49:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.