Sotabase

Career

· Senior Research Scientist, Google DeepMind2025–
· Visiting Researcher, Meta AI NYC2024–
· ML Scientist, Prescient Design2024–
· Undergraduate Student, Princeton University2013–2017
· Software Engineer (SWE), Google
· Research Intern, Google Brain
· PhD Intern, Google Research
· PhD Student, New York University
· Research Intern, Prescient Design
· Software Engineer (SWE), Two Sigma

Publications (64)

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
arXiv.org · 2022
2,201
cited
BBQ: A hand-built bias benchmark for question answering
Findings · 2021
631
cited
Pretraining Language Models with Human Preferences
International Conference on Machine Learning · 2023
279
cited
QuALITY: Question Answering with Long Input Texts, Yes!
North American Chapter of the Association for Computational Linguistics · 2021
197
cited
EvoPrompting: Language Models for Code-Level Neural Architecture Search
Neural Information Processing Systems · 2023
127
cited
Training Language Models with Language Feedback at Scale
arXiv.org · 2023
126
cited
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
International Conference on Learning Representations · 2023
106
cited
Improving Code Generation by Training with Natural Language Feedback
arXiv.org · 2023
91
cited
Seasonal dynamics of bacterial meningitis: a time-series analysis
Lancet Global Health · 2016
79
cited
SQuALITY: Building a Long-Document Summarization Dataset the Hard Way
Conference on Empirical Methods in Natural Language Processing · 2022
55
cited
Training Language Models with Language Feedback
2022
55
cited
Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
Trans. Mach. Learn. Res. · 2023
51
cited
What Do NLP Researchers Believe? Results of the NLP Community Metasurvey
Annual Meeting of the Association for Computational Linguistics · 2022
46
cited
Preference Learning Algorithms Do Not Learn Preference Rankings
Neural Information Processing Systems · 2024
44
cited
Generating Logical Forms from Graph Representations of Text and Entities
Annual Meeting of the Association for Computational Linguistics · 2019
38
cited
Diverse Preference Optimization
arXiv.org · 2025
29
cited
Training Language Models with Natural Language Feedback
2022
24
cited
Learning from Natural Language Feedback
Trans. Mach. Learn. Res. · 2024
21
cited
Reasoning from Radically Incomplete Information: The Case of Containers
2013
21
cited
Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions
LNLS · 2022
19
cited
Sotabase
Angelica Chen | Researcher Profile | Sotabase | Sotabase