Designing decision support systems using counterfactual prediction sets
E Straitouri, MG Rodriguez - ar**
human experts solve classification tasks. Rather than providing single-label predictions …
human experts solve classification tasks. Rather than providing single-label predictions …
Artificial intelligence in soil science: Where do we go now?
Recognizing the fast advancement of artificial intelligence (AI) in soil science, the main
objective of this commentary paper is to discuss how this technology is being incorporated …
objective of this commentary paper is to discuss how this technology is being incorporated …
Human-Driven Active Verification for Efficient and Trustworthy Graph Classification
TC Bui, WS Li - Pacific-Asia Conference on Knowledge Discovery and …, 2024 - Springer
Graph representation learning methods have significantly transformed applications in
various domains. However, their success often comes at the cost of interpretability, hindering …
various domains. However, their success often comes at the cost of interpretability, hindering …
Empowering Humans with Machines: From Explanations to Teaching
H Liu - 2024 - knowledge.uchicago.edu
Artificial intelligence (AI) has demonstrated increasing potential to assist humans in decision-
making tasks. However, AI systems solve problems differently than humans, leading to …
making tasks. However, AI systems solve problems differently than humans, leading to …
Probable-class Nearest-neighbor Explanations Improve AI & Human Accuracy
Nearest neighbors (NN) have traditionally been used both for making final decisions—such
as in Support Vector Machines or $ k $-NN classifiers—and for providing users with …
as in Support Vector Machines or $ k $-NN classifiers—and for providing users with …