Sotabase

Career

· PHD Student, New York University2021–
· AI Research Scientist, Two Sigma2020–2021
· Senior Research Engineer, Allen Institute for Artificial Intelligence (AI2)2019–2020
· Research Engineer, Allen Institute for Artificial Intelligence (AI2)2018–2019
· Software Engineer, Allen Institute for Artificial Intelligence (AI2)2016–2018
· Data Analyst, Akamai Technologies2015–2016
· Teacher, The Wheeler School2014–2015
· Royce Fellow, Brown University2013–2014
· Founder, Kozbox2013–2015
· Research Assistant, Brown University2011–2012
· Residential Advisor, Brown University2011–2011
· Bachelor of Science (B.Sc.), Honors, Mathematics and English, Brown University2010–2014

Publications (53)

CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
North American Chapter of the Association for Computational Linguistics · 2019
2,209
cited
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
Conference on Empirical Methods in Natural Language Processing · 2020
529
cited
Findings of the 2021 Conference on Machine Translation (WMT21)
Conference on Machine Translation · 2021
235
cited
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
AAAI Conference on Artificial Intelligence · 2021
147
cited
Scruples: A Corpus of Community Ethical Judgments on 32, 000 Real-Life Anecdotes
AAAI Conference on Artificial Intelligence · 2020
135
cited
Extracting Scientific Figures with Distantly Supervised Neural Networks
ACM/IEEE Joint Conference on Digital Libraries · 2018
118
cited
Learning from Task Descriptions
Conference on Empirical Methods in Natural Language Processing · 2020
96
cited
G ENIE A Leaderboard for Human-in-the-Loop Evaluation of Text Generation
2021
67
cited
GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation
Conference on Empirical Methods in Natural Language Processing · 2021
28
cited
Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Perfect Reasoners
23
cited
Aioli: A Unified Optimization Framework for Language Model Data Mixing
International Conference on Learning Representations · 2024
16
cited
Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check
Conference on Empirical Methods in Natural Language Processing · 2025
9
cited
Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task
arXiv.org · 2024
5
cited
Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction
Conference on Empirical Methods in Natural Language Processing · 2023
4
cited
Writing Code for NLP Research
Conference on Empirical Methods in Natural Language Processing · 2018
4
cited
Show Your Work with Confidence: Confidence Bands for Tuning Curves
North American Chapter of the Association for Computational Linguistics · 2023
3
cited
Tripod configurations of curves
2014
3
cited
AION-1: Omnimodal Foundation Model for Astronomical Sciences
2025
2
cited
Hyperparameter Loss Surfaces Are Simple Near their Optima
arXiv.org · 2025
1
cited
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback
1
cited
Sotabase