Sophie Hilgard

Harvard University Press — United States

Computer Science · Physical Sciences

8h-index1.1kcitations16works0.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Explainable Artificial Intelligence (XAI)(10), Adversarial Robustness in Machine Learning(9), Machine Learning and Data Classification(5), Social Media and Politics(3), Misinformation and Its Impacts(3)

Publications16 total

Birdwatch: Crowd Wisdom and Bridging Algorithms can Inform Understanding and Reduce the Spread of Misinformation
arXiv (Cornell University)·2022· 34 citedOpen Access
Do Explanations Increase the Effectiveness of AI-Crowd Generated Fake News Warnings?
Proceedings of the International AAAI Conference on Web and Social Media·2022· 43 citedOpen Access
Do explanations increase the effectiveness of AI-crowd generated fake news warnings?
arXiv (Cornell University)·2021· 7 citedOpen Access
Does Fair Ranking Improve Minority Outcomes? Understanding the Interplay of Human and Algorithmic Biases in Online Hiring
2021· 14 citedOpen Access
Feature Attributions and Counterfactual Explanations Can Be Manipulated
arXiv (Cornell University)·2021· 4 citedOpen Access
Counterfactual Explanations Can Be Manipulated
arXiv (Cornell University)·2021· 3 citedOpen Access
Does Fair Ranking Improve Minority Outcomes? Understanding the Interplay\n of Human and Algorithmic Biases in Online Hiring
arXiv (Cornell University)·2020· 3 citedOpen Access
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability
arXiv (Cornell University)·2020· 23 citedOpen Access
How Much Should I Trust You? Modeling Uncertainty of Black Box Explanations.
arXiv (Cornell University)·2020· 10 citedOpen Access
Learning Representations by Humans, for Humans
PsyArXiv (OSF Preprints)·2020· 7 cited
From Predictions to Decisions: Using Lookahead Regularization
arXiv (Cornell University)·2020· 3 citedOpen Access
Fooling LIME and SHAP
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2020· 700 citedOpen Access
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
arXiv (Cornell University)·2019· 169 citedOpen Access
How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods.
arXiv (Cornell University)·2019· 29 citedOpen Access
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation\n Methods
arXiv (Cornell University)·2019· 6 citedOpen Access
Learning Representations by Humans, for Humans
2019· 4 citedOpen Access

Frequent Co-authors

Himabindu Lakkaraju(10), Dylan Slack(8), Sameer Singh(8), Emily Jia(4), Nir Rosenfeld(3), Ziv Epstein(2), N. Foppiani(2), Sanjana Sharma(2), Elena L. Glassman(2), Tom Sühr(2), Mahzarin R. Banaji(2), Jack Cao(2), David C. Parkes(2), David Rand(1), Stefan Wojcik(1), Nick Judd(1), Delia Mocanu(1), Stephen Ragain(1), M. B. Fallin Hunzaker(1), Keith Coleman(1)