Data to 14 Oct 2026

Gender Bias in Neural Natural Language Processing

arXiv 1807.11714 ↗First posted 31 Jul 2018cs.CLcited by 211

Not on the map. Why?

Abstract (arXiv)

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with state-of-the-art neural coreference resolution and textbook RNN-based language models trained on benchmark datasets finds significant gender bias in how models view occupations. We then mitigate bias with CDA: a generic methodology for corpus augmentation via causal interventions that breaks associations between gendered and gender-neutral words. We empirically show that CDA effectively decreases gender bias while preserving accuracy. We also explore the space of mitigation strategies with CDA, a prior approach to word embedding debiasing (WED), and their compositions. We show that CDA outperforms WED, drastically so when word embeddings are trained. For pre-trained embeddings, the two methods can be effectively composed. We also find that as training proceeds on the original data set with gradient descent the gender bias grows as the loss reduces, indicating that the optimization encourages bias; CDA mitigates this behavior.

Key facts. Cited by 211 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 37; 2022: 37; 2023: 55; 2024: 39; 2025: 27; 2026: 16.

211 papers.

Sort:

By area:

2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
2023Bias and Fairness in Large Language Models: A Surveycited by 639
2021A Survey of Data Augmentation Approaches for NLPcited by 409
2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
2021Societal Biases in Language Generation: Progress and Challengescited by 202
2023Gender bias and stereotypes in Large Language Modelscited by 187
2021Alignment of Language Agentscited by 168
2021Gender Bias in Machine Translationcited by 117
2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
2021Sustainable Modular Debiasing of Language Modelscited by 100
2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 98

38 more

2023A Survey on Fairness in Large Language Modelscited by 95
2021Trustworthy AI: A Computational Perspectivecited by 93
2021A Survey on Gender Bias in Natural Language Processingcited by 89
2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
2021On Measures of Biases and Harms in NLPcited by 81
2025LLM Generated Persona is a Promise with a Catchcited by 81
2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
2021NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentationcited by 73
2022Synthetic Data -- what, why and how?cited by 67
2024Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNscited by 65
2022Theories of "Gender" in NLP Bias Researchcited by 62
2024Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypescited by 59
2023TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Modelscited by 58
2024Fairness in Large Language Models: A Taxonomic Surveycited by 58
2021Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Modelscited by 57
2021Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentationcited by 57
2021Directional Bias Amplificationcited by 54
2023Identifying and Mitigating Vulnerabilities in LLM-Integrated Applicationscited by 54
2024Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactionscited by 51
2021Understanding and Mitigating Annotation Bias in Facial Expression Recognitioncited by 50
2021NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternativescited by 46
2021An Investigation of the (In)effectiveness of Counterfactually Augmented Datacited by 42
2022Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversalcited by 40
2025FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steeringcited by 40
2021Balancing out Bias: Achieving Fairness Through Balanced Trainingcited by 34
2021Sparse Interventions in Language Models with Differentiable Maskingcited by 34
2023ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languagescited by 34
2021Revealing Persona Biases in Dialogue Systemscited by 33
2022Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimizationcited by 33
2024Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Modelscited by 33
2021Reason first, then respond: Modular Generation for Knowledge-infused Dialoguecited by 32
2021Towards Robust Classification Model by Counterfactual and Invariant Data Generationcited by 30
2021Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysiscited by 30
2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
2025Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Modelscited by 30
2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
2023CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Modelscited by 28
2023Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventionscited by 28

50 most cited of 211 All 211 (JSON)