mlsanityData to 14 Oct 2026

Queer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models

arXiv 2307.00101 ↗First posted 30 Jun 2023cs.CL cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are trained primarily on minimally processed web text, which exhibits the same wide range of social biases held by the humans who created that content. Consequently, text generated by LLMs can inadvertently perpetuate stereotypes towards marginalized groups, like the LGBTQIA+ community. In this paper, we perform a comparative study of how LLMs generate text describing people with different sexual identities. Analyzing bias in the text generated by an LLM using regard score shows measurable bias against queer people. We then show that a post-hoc method based on chain-of-thought prompting using SHAP analysis can increase the regard of the sentence, representing a promising approach towards debiasing the output of LLMs in this setting.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 30 Jun 2023.

Builds on

22 of 31 references.

References · 22

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  4. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  5. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  6. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  7. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 541
  8. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
  9. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  10. 2017Toward Controlled Generation of Textcited by 272
  11. 2018Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfercited by 191
  12. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 162
10 more
  1. 2021Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologiescited by 128
  2. 2017Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a surveycited by 91
  3. 2020PowerTransformer: Unsupervised Controllable Revision for Biased Language Correctioncited by 59
  4. 2021NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternativescited by 46
  5. 2021They, Them, Theirs: Rewriting with Gender-Neutral Englishcited by 44
  6. 2022Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversalcited by 40
  7. 2021Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lenscited by 30
  8. 2022Text Style Transfer for Bias Mitigation using Masked Language Modelingcited by 28
  9. 2016Neural Text Generation from Structured Data with Application to the Biography Domaincited by 20
  10. 2021Using Sociolinguistic Variables to Reveal Changing Attitudes Towards Sexuality and Gendercited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 9; 2025: 2; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  2. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
  3. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 65
  4. 2024(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advicecited by 63
  5. 2024Fairness in Large Language Models: A Taxonomic Surveycited by 58
  6. 2024Spectral Editing of Activations for Large Language Model Alignmentcited by 56
  7. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  8. 2025BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Modelscited by 11
  9. 2024Fairness in Large Language Models in Three Hourscited by 7
  10. 2025More of the Same: Persistent Representational Harms Under Increased Representationcited by 6
  11. 2024The Life Cycle of Large Language Models: A Review of Biases in Educationcited by 3
  12. 2024Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Wordscited by 1
1 more
  1. 2026Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Oncecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Tasks
  2. 2024Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias
  3. 2024Protected group bias and stereotypes in Large Language Models
  4. 2024Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach
  5. 2023SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models
  6. 2025More Women, Same Stereotypes: Unpacking the Gender Bias Paradox in Large Language Models
  7. 2023Gender bias and stereotypes in Large Language Models
  8. 2024Evaluating Large Language Model Biases in Persona-Steered Generation