mlsanityData to 14 Oct 2026

Disclosure and Mitigation of Gender Bias in LLMs

arXiv 2402.11190 ↗First posted 17 Feb 2024cs.CLcited by 49

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an indirect probing framework based on conditional generation. This approach aims to induce LLMs to disclose their gender bias even without explicit gender or stereotype mentions. We explore three distinct strategies to disclose explicit and implicit gender bias in LLMs. Our experiments demonstrate that all tested LLMs exhibit explicit and/or implicit gender bias, even when gender stereotypes are not present in the inputs. In addition, an increased model size or model alignment amplifies bias in most cases. Furthermore, we investigate three methods to mitigate bias in LLMs via Hyperparameter Tuning, Instruction Guiding, and Debias Tuning. Remarkably, these methods prove effective even in the absence of explicit genders or stereotypes.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

17 of 24 references.

References · 17

  1. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  2. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  3. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  4. 2022Red Teaming Language Models with Language Modelscited by 1,026
  5. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 1,001
  6. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  7. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  8. 2023The Falcon Series of Open Language Modelscited by 535
  9. 2018Gender Bias in Coreference Resolutioncited by 442
  10. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 412
  11. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  12. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 337
5 more
  1. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 194
  2. 2020Towards Debiasing Sentence Representationscited by 171
  3. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  4. 2020Towards Controllable Biases in Language Generationcited by 112
  5. 2023Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Modelcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 17; 2025: 21; 2026: 11.

49 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  2. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 71
  3. 2024"You Gotta be a Doctor, Lin": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendationscited by 33
  4. 2024When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settingscited by 17
  5. 2024A Survey on LLM Inference-Time Self-Improvementcited by 17
  6. 2024Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Biascited by 13
  7. 2025DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysiscited by 12
  8. 2025LLMs for Customized Marketing Content Generation and Evaluation at Scalecited by 9
  9. 2024Are Large Language Models Chameleons? An Attempt to Simulate Social Surveyscited by 8
  10. 2024Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Surveycited by 8
  11. 2024'Since Lawyers are Males..': Examining Implicit Gender Bias in Hindi Language Generation by LLMscited by 8
  12. 2025Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biasescited by 8
37 more
  1. 2024CLIMB: A Benchmark of Clinical Bias in Large Language Modelscited by 7
  2. 2025Rethinking LLM Bias Probing Using Lessons from the Social Sciencescited by 7
  3. 2024Underneath the Numbers: Quantitative and Qualitative Gender Fairness in LLMs for Depression Predictioncited by 6
  4. 2024Hey GPT, Can You be More Racist? Analysis from Crowdsourced Attempts to Elicit Biased Content from Generative AIcited by 6
  5. 2024An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Modelscited by 5
  6. 2024The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Modelscited by 5
  7. 2024How far can bias go? Tracing bias from pretraining data to alignmentcited by 5
  8. 2025The World According to LLMs: How Geographic Origin Influences LLMs' Entity Deduction Capabilitiescited by 5
  9. 2024Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Modelscited by 4
  10. 2025Mitigating Gender Bias via Fostering Exploratory Thinking in LLMscited by 4
  11. 2024Local Contrastive Editing of Gender Stereotypescited by 3
  12. 2025From Idea to Implementation: Evaluating the Influence of Large Language Models in Software Development -- An Opinion Papercited by 3
  13. 2025Gender and content bias in Large Language Models: a case study on Google Gemini 2.0 Flash Experimentalcited by 3
  14. 2024LLM Bias Evaluation: Gender, Racial, and Age Disparities in Occupational and Crime Scenarioscited by 2
  15. 2025LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Modelscited by 2
  16. 2025Relative Bias: A Comparative Framework for Quantifying Bias in LLMscited by 2
  17. 2025Do LLMs have a Gender (Entropy) Bias?cited by 2
  18. 2026An Empirical Study of Collective Behaviors and Social Dynamics in Large Language Model Agentscited by 2
  19. 2026Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluationcited by 2
  20. 2026Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Modelscited by 2
  21. 2025Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Modelscited by 1
  22. 2026QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Taskscited by 1
  23. 2026DeFrame: Debiasing Large Language Models Against Framing Effectscited by 1
  24. 2026A Heuristic Perspective on Debiasing Language Modelscited by 1
  25. 2025Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Modelscited by 0
  26. 2025DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Modelscited by 0
  27. 2025Personalisation or Prejudice? Addressing Geographic Bias in Hate Speech Detection using Debias Tuning in Large Language Modelscited by 0
  28. 2025Overview of the NLPCC 2025 Shared Task: Gender Bias Mitigation Challengecited by 0
  29. 2025Gender Inclusivity Fairness Index (GIFI): A Multilevel Framework for Evaluating Gender Diversity in Large Language Modelscited by 0
  30. 2025Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persiancited by 0
  31. 2025GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Modelscited by 0
  32. 2025Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relationscited by 0
  33. 2026Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detectioncited by 0
  34. 2026How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptionscited by 0
  35. 2026Same Chart, Different Story: Bias in Vision-Language Chart Interpretationcited by 0
  36. 2026Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventionscited by 0
  37. 2026A Systematic Investigation of Bias in Large Language Models for Advertising Relevancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Gender bias and stereotypes in Large Language Models
  2. 2025Unsupervised Concept Vector Extraction for Bias Control in LLMs
  3. 2024Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models
  4. 2023Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model
  5. 2026Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study
  6. 2025More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models
  7. 2025GenderBench: Evaluation Suite for Gender Biases in LLMs
  8. 2025Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective