# Uncovering Implicit Gender Bias in Narratives through Commonsense Inference

arXiv: https://arxiv.org/abs/2109.06437 · HTML: https://mlsanity.com/paper/2109.06437/

## Key facts

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

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation](https://mlsanity.com/paper/2001.05139/) (2020)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [Does Gender Matter? Towards Fairness in Dialogue Systems](https://mlsanity.com/paper/1910.10486/) (2019)
- [The Geometry of Culture: Analyzing Meaning through Word Embeddings](https://mlsanity.com/paper/1803.09288/) (2018)
- [Event2Mind: Commonsense Inference on Events, Intents, and Reactions](https://mlsanity.com/paper/1805.06939/) (2018)
- [Multi-Dimensional Gender Bias Classification](https://mlsanity.com/paper/2005.00614/) (2020)
- [PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction](https://mlsanity.com/paper/2010.13816/) (2020)
- [Empath: Understanding Topic Signals in Large-Scale Text](https://mlsanity.com/paper/1602.06979/) (2016)
- [Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning](https://mlsanity.com/paper/2009.13028/) (2020)
- [Modeling Protagonist Emotions for Emotion-Aware Storytelling](https://mlsanity.com/paper/2010.06822/) (2020)
- ["You are grounded!": Latent Name Artifacts in Pre-trained Language Models](https://mlsanity.com/paper/2004.03012/) (2020)
- [Unsupervised Discovery of Implicit Gender Bias](https://mlsanity.com/paper/2004.08361/) (2020)
- [SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment](https://mlsanity.com/paper/1806.05521/) (2018)
- [Shirtless and Dangerous: Quantifying Linguistic Signals of Gender Bias in an Online Fiction Writing Community](https://mlsanity.com/paper/1603.08832/) (2016)
- [Analyzing Gender Bias within Narrative Tropes](https://mlsanity.com/paper/2011.00092/) (2020)

## Built on by (most cited first, 30 of 32)

- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [Gender Bias in Large Language Models across Multiple Languages](https://mlsanity.com/paper/2403.00277/) (2024)
- [LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education](https://mlsanity.com/paper/2410.14012/) (2024)
- [Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data](https://mlsanity.com/paper/2205.07557/) (2022)
- [Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling](https://mlsanity.com/paper/2310.12902/) (2023)
- [Exploring Safety-Utility Trade-Offs in Personalized Language Models](https://mlsanity.com/paper/2406.11107/) (2024)
- [The "Colonial Impulse" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases](https://mlsanity.com/paper/2401.10535/) (2024)
- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias](https://mlsanity.com/paper/2407.03536/) (2024)
- [Discovering Differences in the Representation of People using Contextualized Semantic Axes](https://mlsanity.com/paper/2210.12170/) (2022)
- [Affective and Dynamic Beam Search for Story Generation](https://mlsanity.com/paper/2310.15079/) (2023)
- [mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans](https://mlsanity.com/paper/2406.04215/) (2024)
- [Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning](https://mlsanity.com/paper/2408.09757/) (2024)
- [Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Ernie](https://mlsanity.com/paper/2309.09120/) (2023)
- [The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories](https://mlsanity.com/paper/2406.16767/) (2024)
- [Implicit Bias in LLMs: A Survey](https://mlsanity.com/paper/2503.02776/) (2025)
- [An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models](https://mlsanity.com/paper/2407.06432/) (2024)
- [Classifying Unreliable Narrators with Large Language Models](https://mlsanity.com/paper/2506.10231/) (2025)
- [A Moral- and Event- Centric Inspection of Gender Bias in Fairy Tales at A Large Scale](https://mlsanity.com/paper/2211.14358/) (2022)
- [Returning to the Start: Generating Narratives with Related Endpoints](https://mlsanity.com/paper/2404.00829/) (2024)
- [Fair In-Context Learning via Latent Concept Variables](https://mlsanity.com/paper/2411.02671/) (2024)
- [Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs](https://mlsanity.com/paper/2412.04576/) (2024)
- [Probing Association Biases in LLM Moderation Over-Sensitivity](https://mlsanity.com/paper/2505.23914/) (2025)
- [Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes](https://mlsanity.com/paper/2508.03292/) (2025)
- [From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text](https://mlsanity.com/paper/2508.09450/) (2025)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)
- [Prioritize Economy or Climate Action? Investigating ChatGPT Response Differences Based on Inferred Political Orientation](https://mlsanity.com/paper/2511.04706/) (2025)
- [ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality](https://mlsanity.com/paper/2402.18797/) (2024)
- [How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language](https://mlsanity.com/paper/2506.06816/) (2025)
- [A Close Reading Approach to Gender Narrative Biases in AI-Generated Stories](https://mlsanity.com/paper/2508.09651/) (2025)

## 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.