mlsanityData to 13 Oct 2026

Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements

arXiv 2205.11374 ↗First posted 23 May 2022cs.CL cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

The growing capability and availability of generative language models has enabled a wide range of new downstream tasks. Academic research has identified, quantified and mitigated biases present in language models but is rarely tailored to downstream tasks where wider impact on individuals and society can be felt. In this work, we leverage one popular generative language model, GPT-3, with the goal of writing unbiased and realistic job advertisements. We first assess the bias and realism of zero-shot generated advertisements and compare them to real-world advertisements. We then evaluate prompt-engineering and fine-tuning as debiasing methods. We find that prompt-engineering with diversity-encouraging prompts gives no significant improvement to bias, nor realism. Conversely, fine-tuning, especially on unbiased real advertisements, can improve realism and reduce bias.

Key facts. Cited by 21 papers in the map (data through 13 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

27 of 45 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2022Training language models to follow instructions with human feedbackcited by 15,856
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,205
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,999
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,229
  7. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,309
  8. 2021Ethical and social risks of harm from Language Modelscited by 964
  9. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  10. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  11. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 559
  12. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
15 more
  1. 2019Release Strategies and the Social Impacts of Language Modelscited by 511
  2. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  3. 2019Measuring Bias in Contextualized Word Representationscited by 275
  4. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  5. 2018Gender Bias in Neural Natural Language Processingcited by 211
  6. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  7. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 181
  8. 2021Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Modelscited by 141
  9. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  10. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
  11. 2021Mitigating Political Bias in Language Models Through Reinforced Calibrationcited by 73
  12. 2019Attenuating Bias in Word Vectorscited by 64
  13. 2018Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examplescited by 34
  14. 2021Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue modelscited by 23
  15. 2021How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?cited by 19

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 10; 2024: 3; 2025: 6; 2026: 2.

21 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 636
  2. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  3. 2023A Survey on Fairness in Large Language Modelscited by 93
  4. 2023DeAR: Debiasing Vision-Language Models with Additive Residualscited by 70
  5. 2025Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Modelscited by 30
  6. 2023A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analyticscited by 18
  7. 2025Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editingcited by 14
  8. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
  9. 2024Natural Language Processing for Human Resources: A Surveycited by 9
  10. 2023Measuring Normative and Descriptive Biases in Language Models Using Census Datacited by 3
  11. 2023All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generationcited by 3
  12. 2024The Life Cycle of Large Language Models: A Review of Biases in Educationcited by 3
9 more
  1. 2025Bias after Prompting: Persistent Discrimination in Large Language Modelscited by 3
  2. 2023Riveter: Measuring Power and Social Dynamics Between Entitiescited by 2
  3. 2025REFER: Mitigating Bias in Opinion Summarisation via Frequency Framed Promptingcited by 2
  4. 2026Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Modelscited by 2
  5. 2023Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the UScited by 0
  6. 2024Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Modelscited by 0
  7. 2025Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisationcited by 0
  8. 2025Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluationcited by 0
  9. 2026When Debiasing Backfires: Counterintuitive Side Effects of Preprocessing-Based Stereotype Mitigationcited by 0