A survey of algorithmic recourse: contrastive explanations and consequential recommendations
Machine learning is increasingly used to inform decision making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …
where decisions have consequential effects on individuals' lives. In these settings, in …
How should the results of artificial intelligence be explained to users?-Research on consumer preferences in user-centered explainable artificial intelligence
Artificial intelligence (AI) has become part of our everyday lives, and its presence and
influence are expected to grow exponentially. Regardless of its expanding impact, the …
influence are expected to grow exponentially. Regardless of its expanding impact, the …
Nice: an algorithm for nearest instance counterfactual explanations
In this paper we propose a new algorithm, named NICE, to generate counterfactual
explanations for tabular data that specifically takes into account algorithmic requirements …
explanations for tabular data that specifically takes into account algorithmic requirements …
Regulating explainable artificial intelligence (XAI) may harm consumers
The most recent artificial intelligence (AI) algorithms lack interpretability. Explainable
artificial intelligence (XAI) aims to address this by explaining AI decisions to customers …
artificial intelligence (XAI) aims to address this by explaining AI decisions to customers …
Investigating the intelligibility of plural counterfactual examples for non-expert users: an explanation user interface proposition and user study
Plural counterfactual examples have been proposed to explain the prediction of a classifier
by offering a user several instances of minimal modifications that may be performed to …
by offering a user several instances of minimal modifications that may be performed to …
When, What, and how should generative artificial intelligence explain to Users?
With the commercialization of ChatGPT, generative artificial intelligence (AI) has been
applied almost everywhere in our lives. However, even though generative AI has become a …
applied almost everywhere in our lives. However, even though generative AI has become a …
[HTML][HTML] A practical exploration of the convergence of Case-Based Reasoning and Explainable Artificial Intelligence
Abstract As Artificial Intelligence (AI) systems become increasingly complex, ensuring their
decisions are transparent and understandable to users has become paramount. This paper …
decisions are transparent and understandable to users has become paramount. This paper …
Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments
M Domnich, J Valja, RM Veski, G Magnifico… - arXiv preprint arXiv …, 2024 - arxiv.org
As machine learning models evolve, maintaining transparency demands more human-
centric explainable AI techniques. Counterfactual explanations, with roots in human …
centric explainable AI techniques. Counterfactual explanations, with roots in human …
Relative Keys: Putting Feature Explanation into Context
Formal feature explanations strictly maintain perfect conformity but are intractable to
compute, while heuristic methods are much faster but can lead to problematic explanations …
compute, while heuristic methods are much faster but can lead to problematic explanations …
Contrastive Explanations of Centralized Multi-agent Optimization Solutions
In many real-world scenarios, agents are involved in optimization problems. Since most of
these scenarios are over-constrained, optimal solutions do not always satisfy all agents …
these scenarios are over-constrained, optimal solutions do not always satisfy all agents …