Lune

ACL Findings2023

Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models

Eddie L. Ungless, Björn Ross, Anne Lauscher

Read at the publisherAsk Lune

Abstract

Warning: many of the images displayed in this paper are offensive and contain implied nudity. They are intended to illustrate potential harms.

Ask Lune

Ask anything. The answer quotes the paper.

Lune reads all of it and the papers around it, then shows you the passages behind every answer.

Questions to start from

Lune answers from

the full paper · 13 top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Cited by top-tier papers13

  1. Products of Positionality: How Tech Workers Shape Identity Concepts in Computer VisionMorgan Klaus Scheuerman, Jed R. BrubakerCHI 2024 · 20 citations
  2. ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image GenerationAkshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo et al.ACL 2024 · 18 citations
  3. Exploring the Use of Abusive Generative AI Models on CivitaiYiluo Wei, Yiming Zhu, Pan Hui, Gareth TysonACM MM 2024 · 11 citations
  4. Amplifying Trans and Nonbinary Voices: A Community-Centred Harm Taxonomy for LLMsEddie L. Ungless, Sunipa Dev, Cynthia L. Bennett, Rebecca Gulotta et al.ACL 2025 · 3 citations
  5. Evaluating Model Bias Requires Characterizing its MistakesIsabela Albuquerque, Jessica Schrouff, David Warde-Farley, Ali Taylan Cemgil et al.ICML 2024 · 3 citations
Ask how each one uses it

Builds on8

  1. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  2. DALL-EVAL: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation ModelsJaemin Cho, Abhay Zala, Mohit BansalICCV 2023 · 283 citations
  3. Everyday Algorithm Auditing: Understanding the Power of Everyday Users in Surfacing Harmful Algorithmic BehaviorsHong Shen, Alicia DeVos, Motahhare Eslami, Kenneth HolsteinCSCW 2021 · 156 citations
  4. Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language TechnologiesSunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, Arjun Subramonian et al.EMNLP 2021 · 113 citations
  5. Perturbation Augmentation for Fairer NLPRebecca Qian, Candace Ross, Jude Fernandes, Eric Michael Smith et al.EMNLP 2022 · 54 citations

Related papers

  1. USD: NSFW Content Detection for Text-to-Image Models via Scene GraphYuyang Zhang, Kangjie Chen, Xudong Jiang, Jiahui Wen et al.USENIX Security 2025
  2. On the Privacy Risks Caused by Images in Academic PapersSze Yiu Chau, Jianyu Lu, Kin Man Leung, Chi Fung Kwan et al.CCS 2026
  3. Relational Context Learning for Human-Object Interaction DetectionSanghyun Kim, Deunsol Jung, Minsu ChoCVPR 2023
  4. 'That's a Red Flag!': How Young Adult Instagram Users Assess Sexual Threats and Perceive Nudity Protection in Direct MessagesAnna Calmbach, Carolyn Guthoff, Matthias Fassl, Katharina KrombholzCCS 2026
  5. "Did They F***ing Consent to That?": Safer Digital Intimacy via Proactive Protection Against Image-Based Sexual AbuseLucy Qin, Vaughn Hamilton, Sharon Wang, Yigit Aydinalp et al.USENIX Security 2024 · 14 citations
Dusk over the sea between two cliffs drawn in fine vertical lines