Sotabase

Career

· PhD student in computer science, UC Berkeley2023–

Publications (13)

Ghostbuster: Detecting Text Ghostwritten by Large Language Models
North American Chapter of the Association for Computational Linguistics · 2023
99
cited
When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks
Conference on Empirical Methods in Natural Language Processing · 2023
85
cited
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination
Conference on Empirical Methods in Natural Language Processing · 2024
55
cited
FairPrism: Evaluating Fairness-Related Harms in Text Generation
Annual Meeting of the Association for Computational Linguistics · 2023
36
cited
The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels
North American Chapter of the Association for Computational Linguistics · 2024
36
cited
Incorporating Worker Perspectives into MTurk Annotation Practices for NLP
Conference on Empirical Methods in Natural Language Processing · 2023
20
cited
Standard Language Ideology in AI-Generated Language
arXiv.org · 2024
11
cited
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models
arXiv.org · 2023
8
cited
Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection
Conference on Empirical Methods in Natural Language Processing · 2023
4
cited
Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree
Conference on Empirical Methods in Natural Language Processing · 2024
3
cited
Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions
Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP · 2025
Characterizing Language Use in a Collaborative Situated Game
arXiv.org · 2025
Sotabase
Eve Fleisig | Researcher Profile | Sotabase | Sotabase