mlsanityData to 7 Oct 2026

Uncovering Implicit Gender Bias in Narratives through Commonsense Inference

arXiv 2109.06437 ↗First posted 14 Sep 2021cs.CLcited by 32

Not on the map. Why?

Abstract (arXiv)

Pre-trained language models learn socially harmful biases from their training corpora, and may repeat these biases when used for generation. We study gender biases associated with the protagonist in model-generated stories. Such biases may be expressed either explicitly ("women can't park") or implicitly (e.g. an unsolicited male character guides her into a parking space). We focus on implicit biases, and use a commonsense reasoning engine to uncover them. Specifically, we infer and analyze the protagonist's motivations, attributes, mental states, and implications on others. Our findings regarding implicit biases are in line with prior work that studied explicit biases, for example showing that female characters' portrayal is centered around appearance, while male figures' focus on intellect.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 14 Sep 2021.

Builds on

30 of 44 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  6. 2018Hierarchical Neural Story Generationcited by 1,182
  7. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  8. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  9. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  10. 2018Gender Bias in Coreference Resolutioncited by 438
  11. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 413
  12. 2019On Measuring Social Biases in Sentence Encoderscited by 397
18 more
  1. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  2. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  3. 2019Queens are Powerful too: Mitigating Gender Bias in Dialogue Generationcited by 152
  4. 2020A Knowledge-Enhanced Pretraining Model for Commonsense Story Generationcited by 116
  5. 2020Towards Controllable Biases in Language Generationcited by 112
  6. 2019Does Gender Matter? Towards Fairness in Dialogue Systemscited by 89
  7. 2018The Geometry of Culture: Analyzing Meaning through Word Embeddingscited by 87
  8. 2018Event2Mind: Commonsense Inference on Events, Intents, and Reactionscited by 82
  9. 2020Multi-Dimensional Gender Bias Classificationcited by 80
  10. 2020PowerTransformer: Unsupervised Controllable Revision for Biased Language Correctioncited by 59
  11. 2016Empath: Understanding Topic Signals in Large-Scale Textcited by 51
  12. 2020Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learningcited by 44
  13. 2020Modeling Protagonist Emotions for Emotion-Aware Storytellingcited by 42
  14. 2020"You are grounded!": Latent Name Artifacts in Pre-trained Language Modelscited by 39
  15. 2020Unsupervised Discovery of Implicit Gender Biascited by 34
  16. 2018SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentimentcited by 25
  17. 2016Shirtless and Dangerous: Quantifying Linguistic Signals of Gender Bias in an Online Fiction Writing Communitycited by 21
  18. 2020Analyzing Gender Bias within Narrative Tropescited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 15; 2025: 10; 2026: 1.

32 papers.

Sort:

By area:

  1. 2024Are Large Language Models Capable of Generating Human-Level Narratives?cited by 78
  2. 2024Gender Bias in Large Language Models across Multiple Languagescited by 35
  3. 2024LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Educationcited by 28
  4. 2022Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Datacited by 27
  5. 2023Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytellingcited by 26
  6. 2024Exploring Safety-Utility Trade-Offs in Personalized Language Modelscited by 26
  7. 2024The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biasescited by 16
  8. 2025Biased Tales: Cultural and Topic Bias in Generating Children's Storiescited by 15
  9. 2024Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Biascited by 13
  10. 2022Discovering Differences in the Representation of People using Contextualized Semantic Axescited by 12
  11. 2023Affective and Dynamic Beam Search for Story Generationcited by 12
  12. 2024mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humanscited by 10
20 more
  1. 2024Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learningcited by 10
  2. 2023Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Erniecited by 8
  3. 2024The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Storiescited by 8
  4. 2025Implicit Bias in LLMs: A Surveycited by 8
  5. 2024An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Modelscited by 4
  6. 2022A Moral- and Event- Centric Inspection of Gender Bias in Fairy Tales at A Large Scalecited by 3
  7. 2024Returning to the Start: Generating Narratives with Related Endpointscited by 3
  8. 2024Fair In-Context Learning via Latent Concept Variablescited by 3
  9. 2024Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMscited by 3
  10. 2025Probing Association Biases in LLM Moderation Over-Sensitivitycited by 3
  11. 2025Classifying Unreliable Narrators with Large Language Modelscited by 3
  12. 2025Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypescited by 2
  13. 2025From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Textcited by 2
  14. 2024A Note on Bias to Completecited by 1
  15. 2025Prioritize Economy or Climate Action? Investigating ChatGPT Response Differences Based on Inferred Political Orientationcited by 1
  16. 2024ARTiST: Automated Text Simplification for Task Guidance in Augmented Realitycited by 0
  17. 2025How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Languagecited by 0
  18. 2025A Close Reading Approach to Gender Narrative Biases in AI-Generated Storiescited by 0
  19. 2025SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validationcited by 0
  20. 2026CASPER in the Machine: Insights into Character Variety in LLM-Generated Storiescited by 0