WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from WikipediaYufang HouAlessandra Pascaleet al.2024NeurIPS 2024
Cookie Consent Has Disparate Impact on Estimation AccuracyErik MiehlingRahul Nairet al.2023NeurIPS 2023
On the Safety of Interpretable Machine Learning: A Maximum Deviation ApproachDennis WeiRahul Nairet al.2022NeurIPS 2022
User Driven Model Adjustment via Boolean Rule ExplanationsElizabeth DalyMassimilliano Mattettiet al.2021AAAI 2021
"I'd never get out of this !?$%# office" redesigning time management for the enterpriseCasey DuganWerner Geyeret al.2012CHI 2012
AIMEE: Interactive model maintenance with rule-based surrogatesOwen CornecRahul Nairet al.2021NeurIPS 2021