Sotabase

Career

· Researcher in Theory of Computation Group, Columbia University

Publications (163)

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
International Conference on Learning Representations · 2023
573
cited
Measuring Bias in Contextualized Word Representations
Proceedings of the First Workshop on Gender Bias in Natural Language Processing · 2019
496
cited
Style Transfer Through Back-Translation
Annual Meeting of the Association for Computational Linguistics · 2018
399
cited
Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings
North American Chapter of the Association for Computational Linguistics · 2019
332
cited
Trusting Your Evidence: Hallucinate Less with Context-aware Decoding
North American Chapter of the Association for Computational Linguistics · 2023
302
cited
Problems With Evaluation of Word Embeddings Using Word Similarity Tasks
RepEval@ACL · 2016
285
cited
Massively Multilingual Word Embeddings
arXiv.org · 2016
274
cited
Metaphor Detection with Cross-Lingual Model Transfer
Annual Meeting of the Association for Computational Linguistics · 2014
268
cited
Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models
International Conference on Learning Representations · 2020
228
cited
Sparse Overcomplete Word Vector Representations
Annual Meeting of the Association for Computational Linguistics · 2015
210
cited
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions
Annual Meeting of the Association for Computational Linguistics · 2020
194
cited
Do Membership Inference Attacks Work on Large Language Models?
arXiv.org · 2024
166
cited
Evaluation of Word Vector Representations by Subspace Alignment
Conference on Empirical Methods in Natural Language Processing · 2015
157
cited
Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models
Conference on Empirical Methods in Natural Language Processing · 2023
147
cited
A Survey of Race, Racism, and Anti-Racism in NLP
Annual Meeting of the Association for Computational Linguistics · 2021
144
cited
Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts
Conference on Empirical Methods in Natural Language Processing · 2019
140
cited
Not All Contexts Are Created Equal: Better Word Representations with Variable Attention
Conference on Empirical Methods in Natural Language Processing · 2015
140
cited
Framing and Agenda-setting in Russian News: a Computational Analysis of Intricate Political Strategies
Conference on Empirical Methods in Natural Language Processing · 2018
138
cited
Morphological Inflection Generation Using Character Sequence to Sequence Learning
North American Chapter of the Association for Computational Linguistics · 2015
138
cited
Demoting Racial Bias in Hate Speech Detection
International Workshop on Natural Language Processing for Social Media · 2020
135
cited
Sotabase