Sotabase

Career

· Research Scientist, Google Research2023–2023
· Senior AI Research Scientist, Meta2023–
· Research Intern, Google Research2022–2022
· Summer Associate, JP Morgan AI Research2019–2019
· PhD in Language and Information Technologies, Carnegie Mellon University2018–2023
· Science for Social Good Fellow, IBM Research2018–2018
· Master of Science in Language Technologies, Carnegie Mellon University2016–2018
· Bachelor of Computer Engineering, Army Institute of Technology, University of Pune2012–2016

Publications (44)

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
International Conference on Learning Representations · 2024
167
cited
Deep Survival Machines: Fully Parametric Survival Regression and Representation Learning for Censored Data With Competing Risks
IEEE journal of biomedical and health informatics · 2020
151
cited
Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking
arXiv.org · 2023
141
cited
Theoretical guarantees on the best-of-n alignment policy
International Conference on Machine Learning · 2024
91
cited
Deep Cox Mixtures for Survival Regression
Machine Learning in Health Care · 2021
78
cited
A toolbox for surfacing health equity harms and biases in large language models
Nature Medicine · 2024
76
cited
Robust Preference Optimization through Reward Model Distillation
Trans. Mach. Learn. Res. · 2024
60
cited
An Entity Resolution Approach to Isolate Instances of Human Trafficking Online
NUT@EMNLP · 2015
34
cited
auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Data
Machine Learning in Health Care · 2022
33
cited
Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation
Annual Meeting of the Association for Computational Linguistics · 2024
31
cited
Counterfactual Phenotyping with Censored Time-to-Events
Knowledge Discovery and Data Mining · 2022
29
cited
Deep Parametric Time-to-Event Regression with Time-Varying Covariates
SPACA · 2021
29
cited
Interpretable subgroup discovery in treatment effect estimation with application to opioid prescribing guidelines
ACM Conference on Health, Inference, and Learning · 2019
27
cited
Transforming and Combining Rewards for Aligning Large Language Models
International Conference on Machine Learning · 2024
25
cited
InfAlign: Inference-aware language model alignment
International Conference on Machine Learning · 2024
19
cited
Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts
2025
8
cited
Nonlinear Semi-Parametric Models for Survival Analysis
arXiv.org · 2019
8
cited
Participatory Personalization in Classification
Neural Information Processing Systems · 2023
7
cited
Risk-Aware Framework Development for Disruption Prediction: Alcator C-Mod and DIII-D Survival Analysis
Journal of fusion energy · 2024
6
cited
Sotabase
Chirag Nagpal | Researcher Profile | Sotabase | Sotabase