Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You

Markedness: Iconicity, economy, and frequency

Joan L. Bybee. 2010 · 2010

Earlier work this paper cites.

The Chicago face database: A free stimulus set of faces and norming data

Debbie S. Ma, Joshua Correll, and Bernd Wittenbrink. 2015 · 2015

Earlier work this paper cites.

Man is to computer programmer as woman is to homemaker? debiasing word embeddings

Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. 2016 · 2016

Earlier work this paper cites.

Semantics derived automatically from language corpora contain human-like biases

Aylin Caliskan, Joanna J. Bryson, and Arvind Narayanan. 2017 · 2017

Earlier work this paper cites.

Fairness in machine learning: Lessons from political philosophy

Reuben Binns. 2018 · 2018

Earlier work this paper cites.

The misgendering machines: Trans/HCI implications of automatic gender recognition

Os Keyes. 2018 · 2018

Earlier work this paper cites.

UDPipe 2.0 prototype at CoNLL 2018 UD shared task

Milan Straka. 2018 · 2018

Earlier work this paper cites.

Fairness definitions explained

Sahil Verma and Julia Rubin. 2018 · 2018

Earlier work this paper cites.

FairGAN: Fairness-aware generative adversarial networks

Depeng Xu, Shuhan Yuan, Lu Zhang, and Xintao Wu. 2018 · 2018

Earlier work this paper cites.

Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond

Mikel Artetxe and Holger Schwenk. 2019 · 2019

Earlier work this paper cites.

Grammatical gender in German influences how role-nouns are interpreted: Evidence from ERPs

Asifa Majid Julia Misersky and Tineke M. Snijders. 2019 · 2019

Earlier work this paper cites.

It’s all in the name: Mitigating gender bias with name-based counterfactual data substitution

Rowan Hall Maudslay, Hila Gonen, Ryan Cotterell, and Simone Teufel. 2019 · 2019

Earlier work this paper cites.

Unmasking contextual stereotypes: Measuring and mitigating BERT’s gender bias

Marion Bartl, Malvina Nissim, and Albert Gatt. 2020 · 2020

Earlier work this paper cites.

SimAlign: High quality word alignments without parallel training data using static and contextualized embeddings

Masoud Jalili Sabet, Philipp Dufter, François Yvon, and Hinrich Schütze. 2020 · 2020

Earlier work this paper cites.

Monolingual and multilingual reduction of gender bias in contextualized representations

Sheng Liang, Philipp Dufter, and Hinrich Schütze. 2020 · 2020

Earlier work this paper cites.

Gender bias in multilingual embeddings and cross-lingual transfer

Jieyu Zhao, Subhabrata Mukherjee, Saghar Hosseini, Kai-Wei Chang, and Ahmed Hassan Awadallah. 2020 · 2020

Earlier work this paper cites.

Evaluating CLIP: Towards characterization of broader capabilities and downstream implications

Original

Sandhini Agarwal, Gretchen Krueger, Jack Clark, Alec Radford, Jong Wook Kim, and Miles Brundage. 2021 · 2021

Earlier work this paper cites.

Understanding and mitigating annotation bias in facial expression recognition

Yunliang Chen and Jungseock Joo. 2021 · 2021

Earlier work this paper cites.

CLIPScore: A reference-free evaluation metric for image captioning

Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021 · 2021

Earlier work this paper cites.

FairFace: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation

Kimmo Kärkkäinen and Jungseock Joo. 2021 · 2021

Earlier work this paper cites.

A survey on bias and fairness in machine learning

Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021 · 2021

Earlier work this paper cites.

Learning transferable visual models from natural language supervision

Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021 · 2021

Earlier work this paper cites.

mT5: A massively multilingual pre-trained text-to-text transformer

Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021 · 2021

Earlier work this paper cites.

How well can text-to-image generative models understand ethical natural language interventions?

Hritik Bansal, Da Yin, Masoud Monajatipoor, and Kai-Wei Chang. 2022 · 2022

Cited alongside, same era.

High-resolution image synthesis with latent diffusion models

Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022 · 2022

Cited alongside, same era.

Photorealistic text-to-image diffusion models with deep language understanding

Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Raphael Gontijo-Lopes, Burcu Karagol Ayan, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi. 2022 · 2022

Cited alongside, same era.

Worst of both worlds: Biases compound in pre-trained vision-and-language models

Tejas Srinivasan and Yonatan Bisk. 2022 · 2022

Cited alongside, same era.

Occupational biases in Norwegian and multilingual language models

Samia Touileb, Lilja Øvrelid, and Erik Velldal. 2022 · 2022

Cited alongside, same era.

Grambank reveals global patterns in the structural diversity of the world’s languages

Hedvig Skirgård, Hannah J. Haynie, Damián E. Blasi, Harald Hammarström, Jeremy Collins, Jay J. Latarche, Jakob Lesage, Tobias Weber, Alena Witzlack-Makarevich, Sam Passmore, Angela Chira, Luke Maurits, Russell Dinnage, Michael Dunn, Ger Reesink, Ruth Singer, Claire Bowern, Patience Epps, Jane Hill, Outi Vesakoski, Martine Robbeets, Noor Karolin Abbas, and et al. 2023 · 2023

Later among the works it cites.

Exploiting cultural biases via homoglyphs in text-to-image synthesis

Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, and Kristian Kersting. 2023 · 2023

Later among the works it cites.

Democratizing neural machine translation with OPUS-MT

Jörg Tiedemann, Mikko Aulamo, Daria Bakshandaeva, Michele Boggia, Stig-Arne Grönroos, Tommi Nieminen, Alessandro Raganato, Yves Scherrer, Raul Vazquez, and Sami Virpioja. 2023 · 2023

Later among the works it cites.

Gender identification beyond the binary and its consequences for social well-being

Miriam Ines Wickham, Félice van Nunspeet, and Naomi Ellemers. 2023 · 2023

Later among the works it cites.

Contrastive language-vision AI models pretrained on web-scraped multimodal data exhibit sexual objectification bias