Machine learning models that convert user-written text descriptions into images are now widely available online and used by millions of users to generate millions of images a day. We investigate the potential for these models to amplify dangerous and complex stereotypes. We find a broad range of ordinary prompts produce stereotypes, including prompts simply mentioning traits, descriptors, occupations, or objects. For example, we find cases of prompting for basic traits or social roles resulting in images reinforcing whiteness as ideal, prompting for occupations resulting in amplification of racial and gender disparities, and prompting for objects resulting in reification of American norms. Stereotypes are present regardless of whether prompts explicitly mention identity and demographic language or avoid such language. Moreover, stereotypes persist despite mitigation strategies; neither user attempts to counter stereotypes by requesting images with specific counter-stereotypes nor institutional attempts to add system “guardrails” have prevented the perpetuation of stereotypes. Our analysis justifies concerns regarding the impacts of today’s models, presenting striking exemplars, and connecting these findings with deep insights into harms drawn from social scientific and humanist disciplines. This work contributes to the effort to shed light on the uniquely complex biases in language-vision models and demonstrates the ways that the mass deployment of text-to-image generation models results in mass dissemination of stereotypes and resulting harms.
Real world applications of machine learning in natural language processing can span many different domains and usually require a huge effort for the annotation of domain specific training data. For this reason, domain adaptation techniques have gained a lot of attention in the last years. In order to derive an effective domain adaptation, a good feature representation across domains is crucial as well as the generalisation ability of the predictive model. In this paper we address the problem of domain adaptation for sentiment classification by combining deep learning, for acquiring a cross-domain high-level feature representation, and ensemble methods, for reducing the cross-domain generalization error. The proposed adaptation framework has been evaluated on a benchmark dataset composed of reviews of four different Amazon category of products, significantly outperforming the state of the art methods.