Sotabase

Career

· Entrepreneur, HERO VP2024–
· Shareholder, Cazamba2020–2021
· Founder, DX Gameworks2020–
· Product manager, full stack developer & UI/UX designer, Remessa Online2020–
· Business Development - Cloud Consulting, ScaleTrend2018–2019
· Opportunities, Sonoma Capital2015–2020

Publications (22)

A survey of safety and trustworthiness of large language models through the lens of verification and validation
Artificial Intelligence Review · 2023
150
cited
A Survey of Text Games for Reinforcement Learning Informed by Natural Language
Transactions of the Association for Computational Linguistics · 2021
32
cited
Hybrid Autoregressive Inference for Scalable Multi-Hop Explanation Regeneration
AAAI Conference on Artificial Intelligence · 2021
26
cited
A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers
North American Chapter of the Association for Computational Linguistics · 2023
15
cited
To be or not to be an Integer? Encoding Variables for Mathematical Text
Findings · 2022
15
cited
TextGraphs 2022 Shared Task on Natural Language Premise Selection
Workshop on Graph-based Methods for Natural Language Processing · 2022
13
cited
Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?
arXiv.org · 2021
12
cited
On the Evaluation of Intelligent Process Automation
AAAI Conference on Artificial Intelligence · 2019
11
cited
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference
Transactions of the Association for Computational Linguistics · 2021
10
cited
Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective
Findings · 2022
10
cited
Interventional Probing in High Dimensions: An NLI Case Study
Findings · 2023
9
cited
Decomposing Natural Logic Inferences in Neural NLI
arXiv.org · 2021
5
cited
Decomposing Natural Logic Inferences for Neural NLI
BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · 2022
4
cited
Estimating the Causal Effects of Natural Logic Features in Neural NLI Models
arXiv.org · 2023
4
cited
Controlling Equational Reasoning in Large Language Models with Prompt Interventions
AAAI Conference on Artificial Intelligence · 2025
3
cited
On the Evaluation of Intelligence Process Automation
arXiv.org · 2020
3
cited
Proceedings of the AAAI-20 Workshop on Intelligent Process Automation (IPA-20)
arXiv.org · 2020
1
cited
Towards Controllable Natural Language Inference through Lexical Inference Types
arXiv.org · 2023
1
cited
EnnCore: End-to-End Conceptual Guarding of Neural Architectures
SafeAI@AAAI · 2022
Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers
arXiv.org · 2022
Sotabase
Andre Freitas | Researcher Profile | Sotabase | Sotabase