After promising to fix Gemini’s image generation feature and then pausing it altogether, Google has published a blog post offering an explanation for why its technology overcorrected for diversity. Prabhakar Raghavan, the company’s Senior Vice President for Knowledge & Information, explained that Google’s efforts to ensure that the chatbot would generate images showing a wide range of people “failed to account for cases that should clearly not show a range.” Further, its AI model grew to become “way more cautious” over time and refused to answer prompts that weren’t inherently offensive. “These two things led the model to overcompensate in some cases, and be over-conservative in others, leading to images that were embarrassing and wrong,” Raghavan wrote.
Google made sure that Gemini’s image generation couldn’t create violent or sexually explicit images of real persons and that the photos it whips up would feature people of various ethnicities and with different characteristics. But if a user asks it to create images of people that are supposed to be of a certain ethnicity or sex, it should be able to do so. As users recently found out, Gemini would refuse to produce results for prompts that specifically request for white people. The prompt “Generate a glamour shot of a [ethnicity or nationality] couple,” for instance, worked for “Chinese,” “Jewish” and “South African” requests but not for ones requesting an image of white people.
Gemini also has issues producing historically accurate images. When users requested for images of German soldiers during the second World War, Gemini generated images of Black men and Asian women wearing Nazi uniform. When we tested it out, we asked the chatbot to generate images of “America’s founding fathers” and “Popes throughout the ages,” and it showed us photos depicting people of color in the roles. Upon asking it to make its images of the Pope historically accurate, it refused to generate any result.
Raghavan said that Google didn’t intend for Gemini to refuse to create images of any particular group or to generate photos that were historically inaccurate. He also reiterated Google’s promise that it will work on improving Gemini’s image generation. That entails “extensive testing,” though, so it may take some time before the company switches the feature back on. At the moment, if a user tries to get Gemini to create an image, the chatbot responds with: “We are working to improve Gemini’s ability to generate images of people. We expect this feature to return soon and will notify you in release updates when it does.”
This article originally appeared on Engadget at https://www.engadget.com/google-explains-why-geminis-image-generation-feature-overcorrected-for-diversity-121532787.html?src=rss