Sonali Parbhoo
Scholar

Sonali Parbhoo

Google Scholar ID: FwEz5s4AAAAJ
Assistant Professor, Imperial College London
Bayesian InferenceCausalityReinforcement LearningInterpretabilityHealthcare
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,251
 
H-index
13
 
i10-index
17
 
Publications
20
 
Co-authors
14
list available
Contact
Emails.parbhoo@imperial.ac.ukCVOpen ↗
Publications
7 items
The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
2025
Cited
0
Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
2025
Cited
0
Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models
2025
Cited
0
Causal Bayesian Optimization with Unknown Graphs
2025
Cited
0
Do regularization methods for shortcut mitigation work as intended?
2025
Cited
0
Feature Importance Depends on Properties of the Data: Towards Choosing the Correct Explanations for Your Data and Decision Trees based Models
2025
Cited
0
Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
2024
Cited
0
Resume (English only)
Co-authors
14 total
Finale Doshi-Velez
Finale Doshi-Velez
Professor, Harvard
Co-author 2
Co-author 2
Co-author 3
Co-author 3
Co-author 4
Co-author 4
Michael C. Hughes
Michael C. Hughes
Assistant Professor of Computer Science, Tufts University
Co-author 6
Co-author 6
Co-author 7
Co-author 7
Co-author 8
Co-author 8