Title |
|---|
 Differential Privacy, Linguistic Fairness, and Training Data Influence:
Impossibility and Possibility Theorems for Multilingual Language ModelsInternational Conference on Machine Learning (ICML), 2023 |
 Improved Target-specific Stance Detection on Social Media Platforms by
Delving into Conversation ThreadsIEEE Transactions on Computational Social Systems (IEEE TCSS), 2022 |
 Influence Functions for Sequence Tagging ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Adapting and Evaluating Influence-Estimation Methods for
Gradient-Boosted Decision TreesJournal of machine learning research (JMLR), 2022 |
 Diagnosing AI Explanation Methods with Folk Concepts of BehaviorConference on Fairness, Accountability and Transparency (FAccT), 2022 |
 AI Explainability 360: Impact and DesignAAAI Conference on Artificial Intelligence (AAAI), 2021 |
 Flexible Instance-Specific Rationalization of NLP ModelsAAAI Conference on Artificial Intelligence (AAAI), 2021 |
