mlsanityData to 14 Oct 2026

On the Mutual Influence of Gender and Occupation in LLM Representations

arXiv 2503.06792 ↗First posted 9 Mar 2025cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

We examine LLM representations of gender for first names in various occupational contexts to study how occupations and the gender perception of first names in LLMs influence each other mutually. We find that LLMs' first-name gender representations correlate with real-world gender statistics associated with the name, and are influenced by the co-occurrence of stereotypically feminine or masculine occupations. Additionally, we study the influence of first-name gender representations on LLMs in a downstream occupation prediction task and their potential as an internal metric to identify extrinsic model biases. While feminine first-name embeddings often raise the probabilities for female-dominated jobs (and vice versa for male-dominated jobs), reliably using these internal gender representations for bias detection remains challenging.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 52 of its 73 references that are in the map. First posted on arXiv 9 Mar 2025.

Builds on

52 of 73 references.

References · 52

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  5. 2018Deep contextualized word representationscited by 2,290
  6. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  8. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  9. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  10. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  11. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 659
  12. 2024OLMo: Accelerating the Science of Language Modelscited by 613
38 more
  1. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  2. 2018Gender Bias in Coreference Resolutioncited by 442
  3. 2019On Measuring Social Biases in Sentence Encoderscited by 398
  4. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  5. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  6. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  7. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  8. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 199
  9. 2020Towards Debiasing Sentence Representationscited by 171
  10. 2018Learning Gender-Neutral Word Embeddingscited by 169
  11. 2020Intrinsic Bias Metrics Do Not Correlate with Application Biascited by 148
  12. 2021Debiasing Pre-trained Contextualised Embeddingscited by 107
  13. 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 103
  14. 2019Evaluating the Underlying Gender Bias in Contextualized Word Embeddingscited by 94
  15. 2019Toward Gender-Inclusive Coreference Resolutioncited by 84
  16. 2022On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representationscited by 75
  17. 2024DE-COP: Detecting Copyrighted Content in Language Models Training Datacited by 74
  18. 2019Attenuating Bias in Word Vectorscited by 64
  19. 2019What's in a Name? Reducing Bias in Bios without Access to Protected Attributescited by 51
  20. 2024Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrievalcited by 51
  21. 2020OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddingscited by 40
  22. 2020"You are grounded!": Latent Name Artifacts in Pre-trained Language Modelscited by 39
  23. 2021Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Modelscited by 39
  24. 2020Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigationcited by 36
  25. 2022Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Biascited by 33
  26. 2024"You Gotta be a Doctor, Lin": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendationscited by 33
  27. 2022SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Modelscited by 22
  28. 2023Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challengescited by 22
  29. 2024Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLPcited by 22
  30. 2024JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Modelscited by 21
  31. 2024First-Person Fairness in Chatbotscited by 20
  32. 2024Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictionscited by 17
  33. 2024From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMscited by 15
  34. 2023Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biasescited by 12
  35. 2024Are Models Biased on Text without Gender-related Language?cited by 10
  36. 2024Susu Box or Piggy Bank: Assessing Cultural Commonsense Knowledge between Ghana and the U.Scited by 9
  37. 2024Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Modelscited by 7
  38. 2025Language Models Predict Empathy Gaps Between Social In-groups and Out-groupscited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Modelscited by 2
  2. 2025'Rich Dad, Poor Lad': How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?cited by 1
  3. 2026Identity-Robust Language Model Generation via Content Integrity Preservationcited by 1
  4. 2026No PUN Intended: Plausible Unknown Names for Person-Centred LLM Evaluationcited by 0