Sotabase

Career

· Assistant Professor of Computer Science and Engineering, University of Michigan2026–
· Research Intern, Microsoft2021–2021
· PhD candidate in Computer Science, Stanford University2019–2025
· Co-founder, Loopye2017–2019
· Intern, Facebook2016–2016
· MS in Computer Science, Federal University of Minas Gerais2015–2017
· Intern, Google2014–2015
· Bachelor of Science in Computer Science, Federal University of Minas Gerais2011–2015
· Researcher, Kempner Institute at Harvard

Publications (44)

Synchromesh: Reliable code generation from pre-trained language models
International Conference on Learning Representations · 2022
193
cited
Hypothesis Search: Inductive Reasoning with Language Models
International Conference on Learning Representations · 2023
152
cited
Solving Math Word Problems by Combining Language Models With Symbolic Solvers
arXiv.org · 2023
142
cited
Parsel🦆: Algorithmic Reasoning with Language Models by Composing Decompositions
Neural Information Processing Systems · 2022
73
cited
Formal Mathematical Reasoning: A New Frontier in AI
arXiv.org · 2024
72
cited
Learning Formal Mathematics From Intrinsic Motivation
Neural Information Processing Systems · 2024
30
cited
Open-domain clarification question generation without question examples
Conference on Empirical Methods in Natural Language Processing · 2021
29
cited
Peano: learning formal mathematical reasoning
Philosophical Transactions of the Royal Society A · 2022
25
cited
Contrastive Reinforcement Learning of Symbolic Reasoning Domains
Neural Information Processing Systems · 2021
24
cited
Parsel: A Unified Natural Language Framework for Algorithmic Reasoning
arXiv.org · 2022
17
cited
Certified Reasoning with Language Models
arXiv.org · 2023
13
cited
dafny-annotator: AI-Assisted Verification of Dafny Programs
arXiv.org · 2024
12
cited
h4rm3l: A Language for Composable Jailbreak Attack Synthesis
International Conference on Learning Representations · 2024
11
cited
Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
arXiv.org · 2024
8
cited
LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
arXiv.org · 2022
7
cited
Left to the Reader: Abstracting Solutions in Mathematical Reasoning
Annual Meeting of the Cognitive Science Society · 2022
6
cited
Can Visual Scratchpads With Diagrammatic Abstractions Augment LLM Reasoning?
ICBINB · 2023
4
cited
From Next-Token to Mathematics: The Learning Dynamics of Mathematical Reasoning in Language Models
2024
4
cited
Position: Formal Mathematical Reasoning - A New Frontier in AI
International Conference on Machine Learning · 2025
3
cited
Pragmatic Code Autocomplete
AAAI Conference on Artificial Intelligence · 2021
3
cited
Sotabase
Gabriel Poesia | Researcher Profile | Sotabase | Sotabase