Sotabase

Career

· Faculty Fellow, New York University (NYU) Center for Data Science2025–
· Research Intern, Bloomberg2023–2023
· Research Intern, Google Research2023–2024
· Research Intern, FAIR (Meta AI)2022–2022
· Ph.D. Research Intern, Allen Institute for AI (AI2)2020–2023
· Lecturer, Bar-Ilan University2020–2021
· PhD in Computer Science, Bar-Ilan University2020–2024
· Teaching Assistant, Bar-Ilan University2019–2021
· MS in Computer Science, Bar-Ilan University2018–2020
· Bachelor's degree, Bar-Ilan University2015–2018
· B.Sc. in Chemistry, Bar-Ilan University2010–2013

Publications (75)

BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
Annual Meeting of the Association for Computational Linguistics · 2021
1,578
cited
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
Annual Meeting of the Association for Computational Linguistics · 2020
470
cited
Measuring and Improving Consistency in Pretrained Language Models
Transactions of the Association for Computational Linguistics · 2021
442
cited
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
Transactions of the Association for Computational Linguistics · 2020
243
cited
LEACE: Perfect linear concept erasure in closed form
Neural Information Processing Systems · 2023
170
cited
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
Neural Information Processing Systems · 2023
156
cited
Contrastive Explanations for Model Interpretability
Conference on Empirical Methods in Natural Language Processing · 2021
110
cited
Linear Adversarial Concept Erasure
International Conference on Machine Learning · 2022
82
cited
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages
North American Chapter of the Association for Computational Linguistics · 2019
74
cited
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction
Conference on Computational Natural Language Learning · 2021
70
cited
DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models
BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · 2022
67
cited
It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · 2020
57
cited
Adversarial Concept Erasure in Kernel Space
Conference on Empirical Methods in Natural Language Processing · 2022
47
cited
Can LSTM Learn to Capture Agreement? The Case of Basque
BlackboxNLP@EMNLP · 2018
45
cited
Ab Antiquo: Neural Proto-language Reconstruction
North American Chapter of the Association for Computational Linguistics · 2019
36
cited
Conformal Nucleus Sampling
Annual Meeting of the Association for Computational Linguistics · 2023
31
cited
Representation Surgery: Theory and Practice of Affine Steering
International Conference on Machine Learning · 2024
31
cited
When Bert Forgets How To POS: Amnesic Probing of Linguistic Properties and MLM Predictions
arXiv.org · 2020
25
cited
Analyzing Gender Representation in Multilingual Models
Workshop on Representation Learning for NLP · 2022
15
cited
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations
BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · 2020
13
cited
Sotabase
Shauli Ravfogel | Researcher Profile | Sotabase | Sotabase