Abstract
Text-to-Image (TTI) models generate images based on text prompts, which often leave certain aspects of the desired image ambiguous. When faced with these ambiguities, TTI models have been shown to exhibit biases in their interpretations. These biases can have societal impacts, e.g., when showing only a certain race for a stated occupation. They can also affect user experience when creating redundancy within a set of generated images instead of spanning diverse possibilities. Here, we introduce MineTheGap - a method for automatically mining prompts that cause a TTI model to generate biased outputs. Our method goes beyond merely detecting bias for a given prompt. Rather, it leverages a genetic algorithm to iteratively refine a pool of prompts, seeking for those that expose biases. This optimization process is driven by a novel bias score, which ranks biases according to their severity, as we validate on a dataset with known biases. For a given prompt, this score is obtained by comparing the distribution of generated images to the distribution of LLM-generated texts that constitute variations on the prompt. Code and examples are available on the project's webpage.
Abstract (translated)
文本到图像（TTI）模型根据文字提示生成图像，这些提示常常会使期望的图像在某些方面产生模糊不清的地方。面对这种模糊性时，TTI模型已被证明会表现出解释偏差。这些偏差可能会对社会造成影响，例如，在显示某种职业时仅展示特定种族的人。它们还可能通过在一个生成的图像集合中制造冗余而不是扩展多样化的可能性来影响用户体验。在这里，我们介绍了MineTheGap——一种自动挖掘会导致TTI模型产生偏向性输出的文字提示的方法。我们的方法不仅限于检测给定提示中的偏见，而是利用遗传算法迭代地优化一个文字提示池，寻找那些暴露偏差的提示。这一优化过程由一个新颖的偏见分数驱动，该分数根据其严重程度对偏见进行排名，我们在具有已知偏见的数据集上验证了这一点。对于每个给定的文字提示，这个分数是通过将生成图像的分布与构成文字提示变体的大型语言模型（LLM）生成文本的分布相比较来获得的。该项目的代码和示例可以在项目网页上找到。
URL
https://arxiv.org/abs/2512.13427
