Himabindu Lakkaraju
Relevante Arbeiten
Meistzitierte Publikationen im Bereich Gesundheit & MedTech
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
2019 · 169 Zit. · arXiv (Cornell University)
The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
2023 · 142 Zit.
Explaining machine learning models with interactive natural language conversations using TalkToModel
2023 · 84 Zit. · Nature Machine Intelligence
Generative AI meets Responsible AI: Practical Challenges and Opportunities
2023 · 83 Zit.
Towards Robust and Reliable Algorithmic Recourse
2021 · 37 Zit. · arXiv (Cornell University)
How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods.
2019 · 29 Zit. · arXiv (Cornell University)
A Human-Centric Perspective on Model Monitoring
2022 · 7 Zit. · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing
Counterfactual Explanations May Not Be the Best Algorithmic Recourse Approach
2025 · 5 Zit.
TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations
2022 · 5 Zit. · arXiv (Cornell University)
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten
2023 · 4 Zit. · arXiv (Cornell University)
Feature Attributions and Counterfactual Explanations Can Be Manipulated
2021 · 4 Zit. · arXiv (Cornell University)
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
2024 · 2 Zit.
Ensuring Actionable Recourse via Adversarial Training.
2020 · 2 Zit. · arXiv (Cornell University)
A Human-Centric Take on Model Monitoring
2022 · 1 Zit. · arXiv (Cornell University)
The First Workshop on AI Behavioral Science
2024 · 0 Zit.