Counterfactual explanations and algorithmic recourses for machine learning: A review
Machine learning plays a role in many deployed decision systems, often in ways that are
difficult or impossible to understand by human stakeholders. Explaining, in a human …
difficult or impossible to understand by human stakeholders. Explaining, in a human …
Towards human-centered explainable ai: A survey of user studies for model explanations
Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A
better understanding of the needs of XAI users, as well as human-centered evaluations of …
better understanding of the needs of XAI users, as well as human-centered evaluations of …
[HTML][HTML] The methodology of studying fairness perceptions in Artificial Intelligence: Contrasting CHI and FAccT
The topic of algorithmic fairness is of increasing importance to the Human–Computer
Interaction research community following accumulating concerns regarding the use and …
Interaction research community following accumulating concerns regarding the use and …
Interrogating the T in FAccT
Fairness, accountability, and transparency are the three conceptual foundations of the
FAccT conference. Transparency, however, has yet to be scrutinized to the same degree as …
FAccT conference. Transparency, however, has yet to be scrutinized to the same degree as …
How AI tools can—and cannot—help organizations become more ethical
D De Cremer, D Narayanan - Frontiers in Artificial Intelligence, 2023 - frontiersin.org
In this paper, we argue that we cannot expect that AI systems—even given more data or
better computational resources—will be more ethical than the humans who develop, deploy …
better computational resources—will be more ethical than the humans who develop, deploy …
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 …
On the Impact of Explanations on Understanding of Algorithmic Decision-Making
Ethical principles for algorithms are gaining importance as more and more stakeholders are
affected by" high-risk" algorithmic decision-making (ADM) systems. Understanding how …
affected by" high-risk" algorithmic decision-making (ADM) systems. Understanding how …
Explainable artificial intelligence: Counterfactual explanations for risk-based decision-making in construction
J Zhan, W Fang, PED Love… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Artificial intelligence (AI) approaches, such as deep learning models, are increasingly used
to determine risks in construction. However, the black-box nature of AI models makes their …
to determine risks in construction. However, the black-box nature of AI models makes their …
Mapping the Design Space of Teachable Social Media Feed Experiences
Social media feeds are deeply personal spaces that reflect individual values and
preferences. However, top-down, platform-wide content algorithms can reduce users' sense …
preferences. However, top-down, platform-wide content algorithms can reduce users' sense …
Counterfactual editing for search result explanation
Recently substantial improvements in neural retrieval methods also bring to light the
inherent blackbox nature of these methods, especially when viewed from an explainability …
inherent blackbox nature of these methods, especially when viewed from an explainability …