A survey of algorithmic recourse: contrastive explanations and consequential recommendations

AH Karimi, G Barthe, B Schölkopf, I Valera - ACM Computing Surveys, 2022 - dl.acm.org
Machine learning is increasingly used to inform decision making in sensitive situations
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

D Kim, Y Song, S Kim, S Lee, Y Wu, J Shin… - … Forecasting and Social …, 2023 - Elsevier
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 …

Nice: an algorithm for nearest instance counterfactual explanations

D Brughmans, P Leyman, D Martens - Data mining and knowledge …, 2024 - Springer
In this paper we propose a new algorithm, named NICE, to generate counterfactual
explanations for tabular data that specifically takes into account algorithmic requirements …

Regulating explainable artificial intelligence (XAI) may harm consumers

B Mohammadi, N Malik, T Derdenger… - Marketing …, 2024 - pubsonline.informs.org
The most recent artificial intelligence (AI) algorithms lack interpretability. Explainable
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

C Bove, MJ Lesot, CA Tijus, M Detyniecki - Proceedings of the 28th …, 2023 - dl.acm.org
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 …

When, What, and how should generative artificial intelligence explain to Users?

S Jang, H Lee, Y Kim, D Lee, J Shin, J Nam - Telematics and Informatics, 2024 - Elsevier
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 …

[HTML][HTML] A practical exploration of the convergence of Case-Based Reasoning and Explainable Artificial Intelligence

P Pradeep, M Caro-Martínez, A Wijekoon - Expert Systems with …, 2024 - Elsevier
Abstract As Artificial Intelligence (AI) systems become increasingly complex, ensuring their
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 …

Relative Keys: Putting Feature Explanation into Context

S An, Y Cao - Proceedings of the ACM on Management of Data, 2024 - dl.acm.org
Formal feature explanations strictly maintain perfect conformity but are intractable to
compute, while heuristic methods are much faster but can lead to problematic explanations …

Contrastive Explanations of Centralized Multi-agent Optimization Solutions

P Zehtabi, A Pozanco, A Bolch, D Borrajo… - Proceedings of the …, 2024 - ojs.aaai.org
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 …