Sotabase

Career

· Assistant Professor CIFAR AI Chair Faculty Member Of Vector Institute, Department of Computer Science, University of Toronto2025–
· Research Scientist, Max Planck Institute for Intelligent Systems2024–
· AI Research Intern, Meta2022–2022
· PHD, ETH Zürich2021–2024
· PHD Student, Max Planck ETH Center for Learning Systems2021–2024
· Ph.D. In Artificial Intelligence, Max Planck Institute for Intelligent Systems2021–2024
· Applied Scientist Intern, Amazon Web Services (AWS)2019–2021
· Undergraduate Research Assistant, Massachusetts Institute of Technology2018–2018
· Undergraduate Research Assistant, MIT Media Lab2017–2018
· Research Assistant, Shanghai Jiao Tong University2017–2017
· Assistant To Country Manager Marketing Assistant, Vega Global2017–2017

Publications (95)

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
AAAI Conference on Artificial Intelligence · 2019
1,264
cited
Deep Learning for Text Style Transfer: A Survey
International Conference on Computational Logic · 2020
277
cited
Membership Inference Attacks against Language Models via Neighbourhood Comparison
Annual Meeting of the Association for Computational Linguistics · 2023
277
cited
Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment
2019
173
cited
Can Large Language Models Infer Causation from Correlation?
International Conference on Learning Representations · 2023
168
cited
CLadder: Assessing Causal Reasoning in Language Models
2023
140
cited
A taxonomy and review of generalization research in NLP
Nature Machine Intelligence · 2022
133
cited
GraphIE: A Graph-Based Framework for Information Extraction
North American Chapter of the Association for Computational Linguistics · 2018
118
cited
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
Neural Information Processing Systems · 2022
117
cited
Mo\^usai: Text-to-Music Generation with Long-Context Latent Diffusion
2023
112
cited
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles
Annual Meeting of the Association for Computational Linguistics · 2020
84
cited
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models
Annual Meeting of the Association for Computational Linguistics · 2022
78
cited
Differentially Private Language Models for Secure Data Sharing
Conference on Empirical Methods in Natural Language Processing · 2022
72
cited
Moûsai: Text-to-Music Generation with Long-Context Latent Diffusion
arXiv.org · 2023
72
cited
Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
Neural Information Processing Systems · 2024
59
cited
CLadder: A Benchmark to Assess Causal Reasoning Capabilities of Language Models
Neural Information Processing Systems · 2023
57
cited
Logical Fallacy Detection
Conference on Empirical Methods in Natural Language Processing · 2022
43
cited
Moûsai: Efficient Text-to-Music Diffusion Models
Annual Meeting of the Association for Computational Linguistics · 2024
39
cited
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
Conference on Empirical Methods in Natural Language Processing · 2021
38
cited
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals
Annual Meeting of the Association for Computational Linguistics · 2024
33
cited
Sotabase