4 papers
Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation
Brian Hyeongseok Kim, Jacqueline L. Mitchell, Chao Wang
Interpreting the inference-time behavior of deep neural networks remains a challenging problem. Existing approaches to counterfactual explanation typically ask: What is the closest…
Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters
Jacqueline L. Mitchell, Brian Hyeongseok Kim, Chenyu Zhou +1
Large language models (LLMs) are increasingly used for program verification, and yet little is known about \emph{how} they reason about program semantics during this process. In th…
Large Language Models for Interpretable Mental Health Diagnosis
Brian Hyeongseok Kim, Chao Wang
We propose a clinical decision support system (CDSS) for mental health diagnosis that combines the strengths of large language models (LLMs) and constraint logic programming (CLP).…
FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks
Brian Hyeongseok Kim, Jingbo Wang, Chao Wang
We propose a method for formally certifying and quantifying individual fairness of deep neural networks (DNN). Individual fairness guarantees that any two individuals who are ident…