3 citations · 3 across the 3 of their papers we have counts for
4 papers
Co-Supervised Tree Synthesis for Interpretable Subgroup Identification and Honest Treatment Effect Inference in Randomized Trials
Evgenii Kuriabov, Zhaoxue Tong, Jia Li
Identifying patient subgroups with heterogeneous treatment effects is central to precision medicine, yet existing approaches face a tension. Black-box methods estimate individualiz…
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
Evgenii Kuriabov, David Miller, Jia Li
In this work, we propose a unified approach for diagnosing misclassification and assessing the robustness of black-box classifiers. Central to our method is an optimization framewo…
Too Categorical to be Human: Emotion Concepts in LLMs and Humans
Sree Bhattacharyya, Evgenii Kuriabov, Lucas Craig +4
Understanding human emotions is central to user-facing AI applications, safety alignment, and the simulation of human behavior. As emotional stimuli shape high-stakes behavior in L…
SynthTree: Co-supervised Local Model Synthesis for Explainable Prediction
Evgenii Kuriabov, Jia Li
Explainable machine learning (XML) has emerged as a major challenge in artificial intelligence (AI). Although black-box models such as Deep Neural Networks and Gradient Boosting of…