Sonali Parbhoo

Computer Science · Physical Sciences

10h-index805citations57works0.12yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Machine Learning in Healthcare(18), Explainable Artificial Intelligence (XAI)(15), Advanced Causal Inference Techniques(10), Health Systems, Economic Evaluations, Quality of Life(9), Statistical Methods and Inference(7)

Publications57 total

Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
arXiv (Cornell University)·2025Open Access
The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
arXiv (Cornell University)·2025Open Access
Do regularization methods for shortcut mitigation work as intended?
arXiv (Cornell University)·2025Open Access
Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models
arXiv (Cornell University)·2025· 1 citedOpen Access
Inverse Transition Learning: Learning Dynamics from Demonstrations
arXiv (Cornell University)·2024Open Access
Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
arXiv (Cornell University)·2024Open Access
Decision-Point Guided Safe Policy Improvement
arXiv (Cornell University)·2024Open Access
Tree-Based Leakage Inspection and Control in Concept Bottleneck Models
arXiv (Cornell University)·2024Open Access
Towards Integrating Personal Knowledge into Test-Time Predictions
arXiv (Cornell University)·2024Open Access
Guarantee Regions for Local Explanations
arXiv (Cornell University)·2024Open Access
Where do doctors disagree? Characterizing Decision Points for Safe Reinforcement Learning in Choosing Vasopressor Treatment.
PubMed·2024
Rethinking Discount Regularization: New Interpretations, Unintended Consequences, and Solutions for Regularization in Reinforcement Learning.
PubMed·2024
Adaptive Experimental Design for Intrusion Data Collection
arXiv (Cornell University)·2023Open Access
Bayesian Inverse Transition Learning for Offline Settings
arXiv (Cornell University)·2023Open Access
Leveraging Factored Action Spaces for Off-Policy Evaluation
arXiv (Cornell University)·2023Open Access
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning.
PubMed·2023· 1 citedOpen Access
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
arXiv (Cornell University)·2023Open Access
Decision-Focused Model-based Reinforcement Learning for Reward Transfer
arXiv (Cornell University)·2023Open Access
Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning
arXiv (Cornell University)·2023· 4 citedOpen Access
Policy Optimization with Sparse Global Contrastive Explanations
arXiv (Cornell University)·2022Open Access
page 1 of 3Next →

Frequent Co-authors

Finale Doshi‐Velez(24), Volker Röth(23), Mario Wieser(13), Aleksander Wieczorek(9), Leo Anthony Celi(7), Mike Wu(6), Maurizio Zazzi(6), Jasmina Bogojeska(4), Jürg Böni(4), Thomas Klimkait(4), Sabine Yerly(4), Manuel Battegay(4), Andri Rauch(4), Enos Bernasconi(4), Matthias Cavassini(4), Roger D. Kouyos(4), Huldrych F. Günthard(4), Karin J. Metzner(4), Michael C. Hughes(4), Omer Gottesman(4)