mlsanityData to 7 Oct 2026

A Robust Bias Mitigation Procedure Based on the Stereotype Content Model

arXiv 2210.14552 ↗First posted 26 Oct 2022cs.CLcited by 24

Not on the map. Why?

Abstract (arXiv)

The Stereotype Content model (SCM) states that we tend to perceive minority groups as cold, incompetent or both. In this paper we adapt existing work to demonstrate that the Stereotype Content model holds for contextualised word embeddings, then use these results to evaluate a fine-tuning process designed to drive a language model away from stereotyped portrayals of minority groups. We find the SCM terms are better able to capture bias than demographic agnostic terms related to pleasantness. Further, we were able to reduce the presence of stereotypes in the model through a simple fine-tuning procedure that required minimal human and computer resources, without harming downstream performance. We present this work as a prototype of a debiasing procedure that aims to remove the need for a priori knowledge of the specifics of bias in the model.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 17 of its 31 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

17 of 31 references.

References · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  3. 2018Deep contextualized word representationscited by 2,285
  4. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  5. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  6. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  7. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 336
  8. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 222
  9. 2021Generating Datasets with Pretrained Language Modelscited by 192
  10. 2020Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biasescited by 167
  11. 2020Intrinsic Bias Metrics Do Not Correlate with Application Biascited by 148
  12. 2020Towards Debiasing NLU Models from Unknown Biasescited by 116
5 more
  1. 2021Debiasing Pre-trained Contextualised Embeddingscited by 107
  2. 2021An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Modelscited by 96
  3. 2022On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representationscited by 75
  4. 2022Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Modelscited by 35
  5. 2021Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Modelcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 12; 2025: 6; 2026: 1.

24 papers.

Sort:

By area:

  1. 2023A Survey on Fairness in Large Language Modelscited by 91
  2. 2024Safeguarding Large Language Models: A Surveycited by 73
  3. 2024Building Guardrails for Large Language Modelscited by 61
  4. 2023Bias Testing and Mitigation in LLM-based Code Generationcited by 53
  5. 2024Navigating LLM Ethics: Advancements, Challenges, and Future Directionscited by 28
  6. 2023Sociodemographic Bias in Language Models: A Survey and Forward Pathcited by 27
  7. 2024MBIAS: Mitigating Bias in Large Language Models While Retaining Contextcited by 15
  8. 2024Social Perception of Faces in a Vision-Language Modelcited by 10
  9. 2024A Multi-LLM Debiasing Frameworkcited by 9
  10. 2025Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Taskscited by 9
  11. 2024Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settingscited by 8
  12. 2024Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Frameworkcited by 8
12 more
  1. 2023Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysiscited by 4
  2. 2025LLMs Reproduce Stereotypes of Sexual and Gender Minoritiescited by 4
  3. 2024Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddingscited by 3
  4. 2024Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIscited by 2
  5. 2024A Taxonomy of Stereotype Content in Large Language Modelscited by 2
  6. 2025Artificial Impressions: Evaluating Large Language Model Behavior Through the Lens of Trait Impressionscited by 2
  7. 2023From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Modelscited by 1
  8. 2024Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Modelscited by 1
  9. 2025Relative Bias: A Comparative Framework for Quantifying Bias in LLMscited by 1
  10. 2025Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstractscited by 0
  11. 2025A Survey on Stereotype Detection in Natural Language Processingcited by 0
  12. 2026Auditing Proprietary Alignment in Large Language Models: A Comparative Framework Without a Ground-Truth Standardcited by 0