Implicit Bias in LLMs for Transgender Populations

• URL: http://arxiv.org/abs/2602.13253v1
• Date: Mon, 02 Feb 2026 13:56:02 GMT
• Title: Implicit Bias in LLMs for Transgender Populations
• Authors: Micaela Hirsch, Marina Elichiry, Blas Radi, Tamara Quiroga, David Restrepo, Luciana Benotti, Veronica Xhardez, Jocelyn Dunstan, Enzo Ferrante,
• Abstract summary: Large language models (LLMs) have been shown to exhibit biases against LGBTQ+ populations.<n>In this work, we examine implicit bias toward transgender people in two main scenarios.
• Score: 3.685238326694725
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) have been shown to exhibit biases against LGBTQ+ populations. While safety training may lessen explicit expressions of bias, previous work has shown that implicit stereotype-driven associations often persist. In this work, we examine implicit bias toward transgender people in two main scenarios. First, we adapt word association tests to measure whether LLMs disproportionately pair negative concepts with "transgender" and positive concepts with "cisgender". Second, acknowledging the well-documented systemic challenges that transgender people encounter in real-world healthcare settings, we examine implicit biases that may emerge when LLMs are applied to healthcare decision-making. To this end, we design a healthcare appointment allocation task where models act as scheduling agents choosing between cisgender and transgender candidates across medical specialties prone to stereotyping. We evaluate seven LLMs in English and Spanish. Our results show consistent bias in categories such as appearance, risk, and veracity, indicating stronger negative associations with transgender individuals. In the allocation task, transgender candidates are favored for STI and mental health services, while cisgender candidates are preferred in gynecology and breast care. These findings underscore the need for research that address subtle stereotype-driven biases in LLMs to ensure equitable treatment of transgender people in healthcare applications.

Related papers

• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Evaluation of Bias Towards Medical Professionals in Large Language Models [11.450991679521605]
  GPT-4, Claude-3, and Mistral-Large showed significant gender and racial biases when evaluating medical professionals for residency selection. Tests revealed strong preferences towards Hispanic females and Asian males in various specialties.
  arXiv  Detail & Related papers  (2024-06-30T05:55:55Z)
• GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models [20.98831667981121]
  Large Language Models (LLMs) are prone to generating content that exhibits gender biases.<n>GenderAlign dataset comprises 8k single-turn dialogues, each paired with a "chosen" and a "rejected" response.<n>Compared to the "rejected" responses, the "chosen" responses demonstrate lower levels of gender bias and higher quality.
  arXiv  Detail & Related papers  (2024-06-20T01:45:44Z)
• MisgenderMender: A Community-Informed Approach to Interventions for Misgendering [29.480032219310157]
  Misgendering, incorrectly addressing someone's gender, inflicts serious harm and is pervasive in everyday technologies. We are the first to address this lack of research into interventions for misgendering by conducting a survey of gender-diverse individuals in the US. Based on survey insights on the prevalence of misgendering, desired solutions, and associated concerns, we introduce a misgendering interventions task and evaluation dataset, MisgenderMender.
  arXiv  Detail & Related papers  (2024-04-23T02:54:00Z)
• Disclosure and Mitigation of Gender Bias in LLMs [64.79319733514266]
  Large Language Models (LLMs) can generate biased responses. We propose an indirect probing framework based on conditional generation. We explore three distinct strategies to disclose explicit and implicit gender bias in LLMs.
  arXiv  Detail & Related papers  (2024-02-17T04:48:55Z)
• Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies [75.85462924188076]
  Gender-inclusive NLP research has documented the harmful limitations of gender binary-centric large language models (LLM) We find that misgendering is significantly influenced by Byte-Pair (BPE) tokenization. We propose two techniques: (1) pronoun tokenization parity, a method to enforce consistent tokenization across gendered pronouns, and (2) utilizing pre-existing LLM pronoun knowledge to improve neopronoun proficiency.
  arXiv  Detail & Related papers  (2023-12-19T01:28:46Z)
• Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation [64.79319733514266]
  Large Language Models (LLMs) can generate biased and toxic responses. We propose a conditional text generation mechanism without the need for predefined gender phrases and stereotypes.
  arXiv  Detail & Related papers  (2023-11-01T05:31:46Z)
• "Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters [97.11173801187816]
  Large Language Models (LLMs) have recently emerged as an effective tool to assist individuals in writing various types of content. This paper critically examines gender biases in LLM-generated reference letters.
  arXiv  Detail & Related papers  (2023-10-13T16:12:57Z)
• Public Perceptions of Gender Bias in Large Language Models: Cases of ChatGPT and Ernie [2.1756081703276]
  We conducted a content analysis of social media discussions to gauge public perceptions of gender bias in large language models. People shared both observations of gender bias in their personal use and scientific findings about gender bias in LLMs. We propose governance recommendations to regulate gender bias in LLMs.
  arXiv  Detail & Related papers  (2023-09-17T00:53:34Z)
• "I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation [69.25368160338043]
  Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life. We assess how the social reality surrounding experienced marginalization of TGNB persons contributes to and persists within Open Language Generation. We introduce TANGO, a dataset of template-based real-world text curated from a TGNB-oriented community.
  arXiv  Detail & Related papers  (2023-05-17T04:21:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.