mlsanityData to 7 Oct 2026

Intersectional Bias in Causal Language Models

arXiv 2107.07691 ↗First posted 16 Jul 2021cs.CL cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

To examine whether intersectional bias can be observed in language generation, we examine GPT-2 and GPT-NEO models, ranging in size from 124 million to ~2.7 billion parameters. We conduct an experiment combining up to three social categories - gender, religion and disability - into unconditional or zero-shot prompts used to generate sentences that are then analysed for sentiment. Our results confirm earlier tests conducted with auto-regressive causal models, including the GPT family of models. We also illustrate why bias may be resistant to techniques that target single categories (e.g. gender, religion and race), as it can also manifest, in often subtle ways, in texts prompted by concatenated social categories. To address these difficulties, we suggest technical and community-based approaches need to combine to acknowledge and address complex and intersectional language model bias.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 26 of its 55 references that are in the map. First posted on arXiv 16 Jul 2021.

Builds on

26 of 55 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  7. 2018Deep contextualized word representationscited by 2,285
  8. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  9. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  10. 2018Hierarchical Neural Story Generationcited by 1,182
  11. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  12. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
14 more
  1. 2018Gender Bias in Coreference Resolutioncited by 438
  2. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
  3. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  4. 2019Evaluating Gender Bias in Machine Translationcited by 247
  5. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  6. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  7. 2020Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biasescited by 167
  8. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  9. 2019Evaluating the Underlying Gender Bias in Contextualized Word Embeddingscited by 94
  10. 2019Gender-preserving Debiasing for Pre-trained Word Embeddingscited by 61
  11. 2019Fine-grained Sentiment Classification using BERTcited by 38
  12. 2020Intersectional Bias in Hate Speech and Abusive Language Datasetscited by 22
  13. 2019Toward Fairness in AI for People with Disabilities: A Research Roadmapcited by 21
  14. 2018AI Fairness for People with Disabilities: Point of Viewcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 10; 2024: 5; 2025: 3; 2026: 2.

24 papers.

Sort:

By area:

  1. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 683
  2. 2023Language Model Tokenizers Introduce Unfairness Between Languagescited by 207
  3. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  4. 2022Datasheet for the Pilecited by 41
  5. 2023AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiologycited by 34
  6. 2024The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiringcited by 29
  7. 2023Global Voices, Local Biases: Socio-Cultural Prejudices across Languagescited by 23
  8. 2025Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Educationcited by 13
  9. 2023Towards Auditing Large Language Models: Improving Text-based Stereotype Detectioncited by 12
  10. 2024Automating Thematic Analysis: How LLMs Analyse Controversial Topicscited by 10
  11. 2022Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Biascited by 8
  12. 2024Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settingscited by 8
12 more
  1. 2023Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Modelscited by 7
  2. 2022Structured Like a Language Model: Analysing AI as an Automated Subjectcited by 6
  3. 2026CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMscited by 6
  4. 2023FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Modelscited by 5
  5. 2024Protected group bias and stereotypes in Large Language Modelscited by 3
  6. 2024Stereotype Detection in LLMs: A Multiclass, Explainable, and Benchmark-Driven Approachcited by 3
  7. 2023Cognitive network science reveals bias in GPT-3, ChatGPT, and GPT-4 mirroring math anxiety in high-school studentscited by 2
  8. 2025Understanding Gender Bias in AI-Generated Product Descriptionscited by 2
  9. 2023Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Modelscited by 1
  10. 2023From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Modelscited by 1
  11. 2025"Accessibility people, you go work on that thing of yours over there": Addressing Disability Inclusion in AI Product Organizationscited by 1
  12. 2026Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilitiescited by 0