Mehar Bhatia

19 papers A* 2Journal 13Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
DeepSeek-R1 Thoughtology: Let's think about LLM reasoning.
Trans. Mach. Learn. Res.
Sara Vera Marjanovic, Arkil Patel, Vaibhav Adlakha, Milad Aghajohari, Parishad BehnamGhader, Mehar Bhatia, Aditi Khandelwal, Austin Kraft, Benno Krojer, Xing Han Lù, Nicholas Meade, Dongchan Shin, Amirhossein Kazemnejad, Gaurav Kamath, Marius Mosbach, Karolina Stanczak, Siva Reddy
2025 — conf
CulturalBench: A Robust, Diverse and Challenging Benchmark for Measuring LMs' Cultural Knowledge Through Human-AI Red-Teaming.
ACL (1)
Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
2025 — conf
CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics.
EMNLP (Findings)
Shravan Nayak, Mehar Bhatia, Xiaofeng Zhang, Verena Rieser, Lisa Anne Hendricks, Sjoerd van Steenkiste, Yash Goyal, Karolina Stanczak, Aishwarya Agrawal
2025 J jnl
CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics.
CoRR
Shravan Nayak, Mehar Bhatia, Xiaofeng Zhang, Verena Rieser, Lisa Anne Hendricks, Sjoerd van Steenkiste, Yash Goyal, Karolina Stanczak, Aishwarya Agrawal
2025 J jnl
DeepSeek-R1 Thoughtology: Let's about LLM Reasoning.
CoRR
Sara Vera Marjanovic, Arkil Patel, Vaibhav Adlakha, Milad Aghajohari, Parishad BehnamGhader, Mehar Bhatia, Aditi Khandelwal, Austin Kraft, Benno Krojer, Xing Han Lù, Nicholas Meade, Dongchan Shin, Amirhossein Kazemnejad, Gaurav Kamath, Marius Mosbach, Karolina Stanczak, Siva Reddy
2025 J jnl
Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4.
CoRR
Zhuozhuo Joy Liu, Farhan Samir, Mehar Bhatia, Laura K. Nelson, Vered Shwartz
2025 J jnl
Societal Alignment Frameworks Can Improve LLM Alignment.
CoRR
Karolina Stanczak, Nicholas Meade, Mehar Bhatia, Hattie Zhou, Konstantin Böttinger, Jeremy Barnes, Jason Stanley, Jessica Montgomery, Richard S. Zemel, Nicolas Papernot, Nicolas Chapados, Denis Therien, Timothy P. Lillicrap, Ana Marasovic, Sylvie Delacroix, Gillian K. Hadfield, Siva Reddy
2025 J jnl
Value Drifts: Tracing Value Alignment During LLM Post-Training.
CoRR
Mehar Bhatia, Shravan Nayak, Gaurav Kamath, Marius Mosbach, Karolina Stanczak, Vered Shwartz, Siva Reddy
2024 J jnl
CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs.
CoRR
Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
2024 J jnl
CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge.
CoRR
Yu Ying Chiu, Liwei Jiang, Maria Antoniak, Chan Young Park, Shuyue Stella Li, Mehar Bhatia, Sahithya Ravi, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
2024 A* conf
From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models.
EMNLP
Mehar Bhatia, Sahithya Ravi, Aditya Chinchure, Eunjeong Hwang, Vered Shwartz
2024 J jnl
From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models.
CoRR
Mehar Bhatia, Sahithya Ravi, Aditya Chinchure, Eunjeong Hwang, Vered Shwartz
2023 A* conf
GD-COMET: A Geo-Diverse Commonsense Inference Model.
EMNLP
Mehar Bhatia, Vered Shwartz
2023 J jnl
GD-COMET: A Geo-Diverse Commonsense Inference Model.
CoRR
Mehar Bhatia, Vered Shwartz
2022 — conf
Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems.
COMAD/CODS
Anubha Kabra, Mehar Bhatia, Yaman Kumar Singla, Junyi Jessy Li, Rajiv Ratn Shah
2021 — conf
One to Rule Them All: Towards Joint Indic Language Hate Speech Detection.
FIRE (Working Notes)
Mehar Bhatia, Tenzin Singhay Bhotia, Akshat Agarwal, Prakash Ramesh, Shubham Gupta, Kumar Shridhar, Felix Laumann, Ayushman Dash
2021 J jnl
One to rule them all: Towards Joint Indic Language Hate Speech Detection.
CoRR
Mehar Bhatia, Tenzin Singhay Bhotia, Akshat Agarwal, Prakash Ramesh, Shubham Gupta, Kumar Shridhar, Felix Laumann, Ayushman Dash
2021 J jnl
Perception Point: Identifying Critical Learning Periods in Speech for Bilingual Networks.
CoRR
Anuj Saraswat, Mehar Bhatia, Yaman Kumar Singla, Changyou Chen, Rajiv Ratn Shah
2020 J jnl
Calling Out Bluff: Attacking the Robustness of Automatic Scoring Systems with Simple Adversarial Testing.
CoRR
Yaman Kumar, Mehar Bhatia, Anubha Kabra, Junyi Jessy Li, Di Jin, Rajiv Ratn Shah