Publications

2023

1. 

   StereoMap: Quantifying the Awareness of Human-like Stereotypes in Large Language Models

   Sullam Jeoung, Yubin Ge, and Jana Diesner

   arXiv preprint arXiv:2310.13673, 2023

   PDF Code

2. 

   Examining the Causal Impact of First Names on Language Models: The Case of Social Commonsense Reasoning

   Sullam Jeoung, Jana Diesner, and Halil Kilicoglu

   In ACL Workshop on Trustworthy Natural Language Processing (TrustNLP 2023), 2023

   PDF Code
3. Detection and Mitigation of the Negative Impact of Dataset Extractivity on Abstractive Summarization

   Yubin Ge, Sullam Jeoung, Ly Dinh, and 1 more author

   In Findings of the Association for Computational Linguistics: ACL 2023, 2023
4. Unlearning bias in language models by partitioning gradients

   Charles Yu, Sullam Jeoung, Anish Kasi, and 2 more authors

   In Findings of the Association for Computational Linguistics: ACL 2023, 2023
5. Moving Beyond Stance Detection in Cross-Cutting Communication Analysis

   Rezvaneh Rezapour, Daniela Delgado Ramos, Sullam Jeoung, and 1 more author

   In International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation, 2023
6. Are we projecting gender biases to ungendered things? Differences in referring to female versus male named hurricanes in 33 years of news coverage

   Ly Dinh, Janina Sarol, Sullam Jeoung, and 1 more author

   Computational Communication Research, 2023

2022

1. What changed? Investigating Debiasing Methods using Causal Mediation Analysis

   Sullam Jeoung, and Jana Diesner

   In NAACL Workshop on Gender Bias in Natural Language Processing (GeBNLP), 2022