Leveraging explanations in interactive machine learning: An overview

S Teso, Ö Alkan, W Stammer, E Daly - Frontiers in Artificial …, 2023 - frontiersin.org
Explanations have gained an increasing level of interest in the AI and Machine Learning
(ML) communities in order to improve model transparency and allow users to form a mental …

[HTML][HTML] Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions

L Longo, M Brcic, F Cabitza, J Choi, R Confalonieri… - Information …, 2024 - Elsevier
Understanding black box models has become paramount as systems based on opaque
Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response …

[PDF][PDF] Good Explanations in Explainable Artificial Intelligence (XAI): Evidence from Human Explanatory Reasoning.

RMJ Byrne - IJCAI, 2023 - ijcai.org
Insights from cognitive science about how people understand explanations can be
instructive for the development of robust, user-centred explanations in eXplainable Artificial …

[HTML][HTML] On the robustness of sparse counterfactual explanations to adverse perturbations

M Virgolin, S Fracaros - Artificial Intelligence, 2023 - Elsevier
Counterfactual explanations (CEs) are a powerful means for understanding how decisions
made by algorithms can be changed. Researchers have proposed a number of desiderata …

[HTML][HTML] The role of humanization and robustness of large language models in conversational artificial intelligence for individuals with depression: a critical analysis

A Ferrario, J Sedlakova, M Trachsel - JMIR Mental Health, 2024 - mental.jmir.org
Large language model (LLM)–powered services are gaining popularity in various
applications due to their exceptional performance in many tasks, such as sentiment analysis …

Robustness implies fairness in causal algorithmic recourse

AR Ehyaei, AH Karimi, B Schölkopf… - Proceedings of the 2023 …, 2023 - dl.acm.org
Algorithmic recourse discloses the internal procedures of a black-box decision process
where decisions have significant consequences by providing recommendations to empower …

Finding regions of counterfactual explanations via robust optimization

D Maragno, J Kurtz, TE Röber… - INFORMS Journal …, 2024 - pubsonline.informs.org
Counterfactual explanations (CEs) play an important role in detecting bias and improving
the explainability of data-driven classification models. A CE is a minimal perturbed data …

Setting the right expectations: Algorithmic recourse over time

J Fonseca, A Bell, C Abrate, F Bonchi… - Proceedings of the 3rd …, 2023 - dl.acm.org
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of
this, algorithmic recourse, the principle wherein individuals should be able to take action …

[HTML][HTML] Mathematical optimization modelling for group counterfactual explanations

E Carrizosa, J Ramírez-Ayerbe, DR Morales - European Journal of …, 2024 - Elsevier
Counterfactual Analysis has shown to be a powerful tool in the burgeoning field of
Explainable Artificial Intelligence. In Supervised Classification, this means associating with …

Attribution-based explanations that provide recourse cannot be robust

H Fokkema, R De Heide, T Van Erven - Journal of Machine Learning …, 2023 - jmlr.org
Different users of machine learning methods require different explanations, depending on
their goals. To make machine learning accountable to society, one important goal is to get …