mlsanityData to 14 Oct 2026

In-Contextual Gender Bias Suppression for Large Language Models

arXiv 2309.07251 ↗First posted 13 Sep 2023cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

Despite their impressive performance in a wide range of NLP tasks, Large Language Models (LLMs) have been reported to encode worrying-levels of gender biases. Prior work has proposed debiasing methods that require human labelled examples, data augmentation and fine-tuning of LLMs, which are computationally costly. Moreover, one might not even have access to the model parameters for performing debiasing such as in the case of closed LLMs such as GPT-4. To address this challenge, we propose bias suppression that prevents biased generations of LLMs by simply providing textual preambles constructed from manually designed templates and real-world statistics, without accessing to model parameters. We show that, using CrowsPairs dataset, our textual preambles covering counterfactual statements can suppress gender biases in English LLMs such as LLaMA2. Moreover, we find that gender-neutral descriptions of gender-biased objects can also suppress their gender biases. Moreover, we show that bias suppression has acceptable adverse effect on downstream task performance with HellaSwag and COPA.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 36 of its 54 references that are in the map. First posted on arXiv 13 Sep 2023.

Builds on

36 of 54 references.

References · 36

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  5. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  7. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  8. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  10. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  11. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  12. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
24 more
  1. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  2. 2018Gender Bias in Coreference Resolutioncited by 442
  3. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
  4. 2021Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPcited by 337
  5. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  6. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  7. 2022Prompting GPT-3 To Be Reliablecited by 260
  8. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 243
  9. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 224
  10. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  11. 2019Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphologycited by 200
  12. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 173
  13. 2021Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologiescited by 128
  14. 2021Debiasing Pre-trained Contextualised Embeddingscited by 107
  15. 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 103
  16. 2021Sustainable Modular Debiasing of Language Modelscited by 100
  17. 2019Toward Gender-Inclusive Coreference Resolutioncited by 84
  18. 2019Gender-preserving Debiasing for Pre-trained Word Embeddingscited by 61
  19. 2021Unmasking the Mask -- Evaluating Social Biases in Masked Language Modelscited by 60
  20. 2022Gender Bias in Masked Language Models for Multiple Languagescited by 60
  21. 2021Discrete and Soft Prompting for Multilingual Modelscited by 49
  22. 2022Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Taskscited by 48
  23. 2021Dictionary-based Debiasing of Pre-trained Word Embeddingscited by 24
  24. 2022Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruningcited by 21

Built on by

Cited by year (2026 to 14 Oct)

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

12 papers.

  1. 2024Evaluating Gender Bias in Large Language Models via Chain-of-Thought Promptingcited by 50
  2. 2024SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanationscited by 38
  3. 2025Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Modelscited by 18
  4. 2024Causal-Guided Active Learning for Debiasing Large Language Modelscited by 15
  5. 2024Hire Me or Not? Examining Language Model's Behavior with Occupation Attributescited by 5
  6. 2024Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approachcited by 3
  7. 2024Evaluating Gender Bias in Large Language Modelscited by 2
  8. 2025BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responsescited by 2
  9. 2026Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Modelscited by 2
  10. 2026Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Modelscited by 1
  11. 2026DeFrame: Debiasing Large Language Models Against Framing Effectscited by 1
  12. 2025Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Modelscited by 0