Mehar Bhatia
Scholar

Mehar Bhatia

Google Scholar ID: F1efoLgAAAAJ
PhD Student at McGill University & MILA
Natural Language ProcessingAI AlignmentAI Safety
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
187
 
H-index
8
 
i10-index
8
 
Publications
12
 
Co-authors
8
list available
Contact
Emailmehar.bhatia@mila.quebecCVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
6 items
Value Drifts: Tracing Value Alignment During LLM Post-Training
2025
Cited
0
CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics
2025
Cited
0
Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4
2025
Cited
0
DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
2025
Cited
0
Societal Alignment Frameworks Can Improve LLM Alignment
2025
Cited
0
CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs
arXiv.org · 2024
Cited
25
Resume (English only)
Co-authors
8 total
Vered Shwartz
Vered Shwartz
University of British Columbia
Yejin Choi
Yejin Choi
Stanford University / NVIDIA
Yulia Tsvetkov
Yulia Tsvetkov
University of Washington
Siva Reddy
Siva Reddy
McGill University, Mila Quebec AI Institute
Karolina Stańczak
Karolina Stańczak
ETH Zurich
Marius Mosbach
Marius Mosbach
Mila - Quebec AI Institute, McGill University
Aishwarya Agrawal
Aishwarya Agrawal
University of Montreal, Mila, Google DeepMind
Verena Rieser
Verena Rieser
Google DeepMind