• Overviews
  • Meade et al 2021 - An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
• Papers
  • Schick et al 2021 - Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP

• Gupta et al 2023 - Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs

• Overviews
  • Sun et al 2019 - Mitigating Gender Bias in Natural Language Processing: Literature Review
• Papers
  • Lakoff 1973 - Language and Woman's Place Linguistics paper from 1973 by Robin Lakoff, often credited for making language and gender a major debate in linguistics.
  • Bolukbasi et al 2016 - Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
  • Zhao et al 2017 - Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
  • Gonen & Goldberg 2019 - Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them
  • Zhao et al 2019 - Gender Bias in Contextualized Word Embeddings
  • Zmigrod et al 2019 - Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology
  • BUG dataset: Levy et al 2021 - Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation
  • Gupta et al 2022 - Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
  • Data Augmentation
    • Zmigrod et al 2019 - Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology
• In Applications
  • Coreference Resolution
    • Zhao et al 2018 - Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods Introduces Winobias coreference dataset. They use data-augmentation and word-embedding debiasing techniques, to remove bias in coref systems without reducing performance on existing coref datasets.
      • SoWinoBias: Dawkins 2021 - Second Order WinoBias (SoWinoBias) Test Set for Latent Gender Bias Detection in Coreference Resolution
    • Zhao et al 2019 - Gender Bias in Contextualized Word Embeddings
  • Dialog
    • Dinan et al 2020 - Multi-Dimensional Gender Bias Classification dataset
  • Machine Translation
• Datasets
  • MDGender: Dinan et al 2020 - Multi-Dimensional Gender Bias Classification dataset
• Resources
  • Gendered word lists
    • MDGender

Includes for example, annotation artifacts. For an introduction, read Gururangan 2018 and Zellers 2018.

• Poliak et al 2018 - Hypothesis Only Baselines in Natural Language Inference
• Gururangan et al 2018 - Annotation Artifacts in Natural Language Inference Data
• McCoy et al 2019 - Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
• Geva et al 2019 - Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets
• Schwartz & Stanovsky 2022 - On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations

• Adversarial Filtering
  • Zellers et al 2018 - SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference Introduces Adversarial Filtering to try to eliminate dataset bias
  • Bartolo et al 2020 - Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension

• Tutorial: Bias and Fairness in Natural Language Processing

• Kai-Wei Chang
• Mark Yatskar

• Ethics
• Robustness in NLP
• Fairness