MineTheGap: Automatic Mining of Biases in Text-to-Image Models

• URL: http://arxiv.org/abs/2512.13427v1
• Date: Mon, 15 Dec 2025 15:17:02 GMT
• Title: MineTheGap: Automatic Mining of Biases in Text-to-Image Models
• Authors: Noa Cohen, Nurit Spingarn-Eliezer, Inbar Huberman-Spiegelglas, Tomer Michaeli,
• Abstract summary: Text-to-Image (TTI) models generate images based on text prompts, which often leave certain aspects of the desired image ambiguous.<n>These biases can have societal impacts, e.g., when showing only a certain race for a stated occupation.<n>Here, we introduce MineTheGap - a method for automatically mining prompts that cause a TTI model to generate biased outputs.
• Score: 34.34264237099797
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search [18.386455479798574]
  Bias-Guided Prompt Search (BGPS) is a framework that automatically generates prompts that aim to maximize the presence of biases in images.<n>BGPS comprises two components: (1) an LLM instructed to produce attribute-neutral prompts and (2) attribute classifiers acting on the TTI's internal representations.<n>We conduct extensive experiments on Stable Diffusion 1.5 and a state-of-the-art debiased model and discover an array of subtle and previously undocumented biases.
  arXiv  Detail & Related papers  (2025-12-09T15:39:04Z)
• Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis [97.37770785712475]
  We present a generation-based debiasing framework for object detection.<n>Our method significantly narrows the performance gap for underrepresented object groups.
  arXiv  Detail & Related papers  (2025-10-21T02:19:12Z)
• AutoDebias: Automated Framework for Debiasing Text-to-Image Models [6.581606189725493]
  Text-to-Image (T2I) models generate high-quality images from text prompts but often exhibit unintended social biases.<n>We propose AutoDebias, a framework that automatically identifies and mitigates harmful biases in T2I models without prior knowledge of specific bias types.<n>We evaluate the framework on a benchmark covering over 25 bias scenarios, including challenging cases where multiple biases occur simultaneously.
  arXiv  Detail & Related papers  (2025-08-01T09:05:45Z)
• Using LLMs as prompt modifier to avoid biases in AI image generators [0.0]
  Large Language Models (LLMs) can reduce biases in text-to-image generation systems by modifying user prompts.<n>Our experiments with Stable Diffusion XL, 3.5 and Flux demonstrate that LLM-modified prompts significantly increase image diversity and reduce bias without the need to change the image generators themselves.
  arXiv  Detail & Related papers  (2025-04-15T11:52:20Z)
• GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models [75.04426753720553]
  We propose a framework to identify, quantify, and explain biases in an open set setting. This pipeline leverages a Large Language Model (LLM) to propose biases starting from a set of captions. We show two variations of this framework: OpenBias and GradBias.
  arXiv  Detail & Related papers  (2024-08-29T16:51:07Z)
• AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation [53.65701943405546]
  We learn adaptive inclusive tokens to shift the attribute distribution of the final generative outputs. Our method requires neither explicit attribute specification nor prior knowledge of the bias distribution. Our method achieves comparable performance to models that require specific attributes or editing directions for generation.
  arXiv  Detail & Related papers  (2024-06-18T17:22:23Z)
• Fair Text-to-Image Diffusion via Fair Mapping [32.02815667307623]
  We propose a flexible, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image diffusion model. By effectively addressing the issue of implicit language bias, our method produces more fair and diverse image outputs.
  arXiv  Detail & Related papers  (2023-11-29T15:02:01Z)
• ITI-GEN: Inclusive Text-to-Image Generation [56.72212367905351]
  This study investigates inclusive text-to-image generative models that generate images based on human-written prompts. We show that, for some attributes, images can represent concepts more expressively than text. We propose a novel approach, ITI-GEN, that leverages readily available reference images for Inclusive Text-to-Image GENeration.
  arXiv  Detail & Related papers  (2023-09-11T15:54:30Z)
• Word-Level Explanations for Analyzing Bias in Text-to-Image Models [72.71184730702086]
  Text-to-image (T2I) models can generate images that underrepresent minorities based on race and sex. This paper investigates which word in the input prompt is responsible for bias in generated images.
  arXiv  Detail & Related papers  (2023-06-03T21:39:07Z)
• Mitigating Test-Time Bias for Fair Image Retrieval [18.349154934096784]
  We address the challenge of generating fair and unbiased image retrieval results given neutral textual queries. We introduce a straightforward technique, Post-hoc Bias Mitigation, that post-processes the outputs from the pre-trained vision-language model. Our approach achieves the lowest bias, compared with various existing bias-mitigation methods, in text-based image retrieval result.
  arXiv  Detail & Related papers  (2023-05-23T21:31:16Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Discovering and Mitigating Visual Biases through Keyword Explanation [66.71792624377069]
  We propose the Bias-to-Text (B2T) framework, which interprets visual biases as keywords. B2T can identify known biases, such as gender bias in CelebA, background bias in Waterbirds, and distribution shifts in ImageNet-R/C. B2T uncovers novel biases in larger datasets, such as Dollar Street and ImageNet.
  arXiv  Detail & Related papers  (2023-01-26T13:58:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.