Publications

Google Scholar

* signifies equal contribution

signifies less representative papers, signifies more representative papers

Papers

• Large Language Models Cannot Replace Human Participants Because They Cannot Portray Identity Groups
  Angelina Wang, Jamie Morgenstern, John P. Dickerson
  Preprint

• Measuring Machine Learning Harms from Stereotypes: Requires Understanding Who is Being Harmed by Which Errors in What Ways
  Angelina Wang, Xuechunzi Bai, Solon Barocas, Su Lin Blodgett
  EAAMO 2023

• Overwriting Pretrained Bias with Finetuning Data
  Angelina Wang and Olga Russakovsky
  ICCV 2023 - Oral

• Gender Artifacts in Visual Datasets
  Nicole Meister*, Dora Zhao*, Angelina Wang, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky
  ICCV 2023

• Against Predictive Optimization: On the Legitimacy of Decision-Making Algorithms that Optimize Predictive Accuracy [website]
  Angelina Wang*, Sayash Kapoor*, Solon Barocas, Arvind Narayanan
  FAccT 2023; Journal of Responsible Computing 2023

• Taxonomizing and Measuring Representational Harms: A Look at Image Tagging
  Jared Katzman*, Angelina Wang*, Morgan Scheuerman, Su Lin Blodgett, Kristen Laird, Hanna Wallach, Solon Barocas
  AAAI 2023

• Manipulative Tactics are the Norm in Political Emails: Evidence from 100K emails from the 2020 U.S. Election Cycle [website]
  Arunesh Mathur, Angelina Wang, Carsten Schwemmer, Maia Hamin, Brandon M. Stewart, Arvind Narayanan
  Big Data & Society 2023

• Measuring Representational Harms in Image Captioning [4 min video] [15 min video]
  Angelina Wang, Solon Barocas, Kristen Laird, Hanna Wallach
  FAccT 2022

• Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation [4 min video] [15 min video]
  Angelina Wang, Vikram V. Ramaswamy, Olga Russakovsky
  FAccT 2022

• REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets
  Angelina Wang, Alexander Liu, Ryan Zhang, Anat Kleiman, Leslie Kim, Dora Zhao, Iroha Shirai, Arvind Narayanan, Olga Russakovsky
  IJCV 2022 (extended version of ECCV 2020 publication)

• Understanding and Evaluating Racial Biases in Image Captioning
  Dora Zhao, Angelina Wang, Olga Russakovsky
  ICCV 2021

• Directional Bias Amplification [video] [poster]
  Angelina Wang and Olga Russakovsky
  ICML 2021

• The Limits of Global Inclusion in AI Development
  Alan Chan*, Chinasa T. Okolo*, Zachary Terner*, Angelina Wang*
  AAAI 2021 Workshop on Reframing Diversity in AI - Spotlight

• REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets [video]
  ^{alternate name: “BImAgeS: BIAS is in all images”}
  Angelina Wang, Arvind Narayanan, Olga Russakovsky
  ECCV 2020 - Spotlight (top 5% of submissions)

• Learning Robotic Manipulation through Visual Planning and Acting
  Angelina Wang, Thanard Kurutach, Kara Liu, Pieter Abbeel, Aviv Tamar
  Robotics: Science and Systems 2019

• Safer Classification by Synthesis
  William Wang, Angelina Wang, Aviv Tamar, Xi Chen, Pieter Abbeel
  NeurIPS 2017 Aligned AI Workshop

Other

• A Tale of Two Conferences: FAccT and ICML 2022
  Medium 2022

• Building a Bridge with Concrete… Examples
  Freedom to Tinker Blog 2020

• FTC Comment on Children’s Online Privacy Protection Act (COPPA) Rule
  2019