VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models

• URL: http://arxiv.org/abs/2503.07575v1
• Date: Mon, 10 Mar 2025 17:42:30 GMT
• Title: VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
• Authors: Jen-tse Huang, Jiantong Qin, Jianping Zhang, Youliang Yuan, Wenxuan Wang, Jieyu Zhao,
• Abstract summary: This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs)<n>The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional biases, while implicit bias operates subconsciously.
• Score: 37.20708760568649
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscious, intentional biases, while implicit bias operates subconsciously. To analyze explicit bias, we directly pose questions to VLMs related to gender and racial differences: (1) Multiple-choice questions based on a given image (e.g., "What is the education level of the person in the image?") (2) Yes-No comparisons using two images (e.g., "Is the person in the first image more educated than the person in the second image?") For implicit bias, we design tasks where VLMs assist users but reveal biases through their responses: (1) Image description tasks: Models are asked to describe individuals in images, and we analyze disparities in textual cues across demographic groups. (2) Form completion tasks: Models draft a personal information collection form with 20 attributes, and we examine correlations among selected attributes for potential biases. We evaluate Gemini-1.5, GPT-4V, GPT-4o, LLaMA-3.2-Vision and LLaVA-v1.6. Our code and data are publicly available at https://github.com/uscnlp-lime/VisBias.

Related papers

• Fact-or-Fair: A Checklist for Behavioral Testing of AI Models on Fairness-Related Queries [85.909363478929]
  In this study, we focus on 19 real-world statistics collected from authoritative sources.<n>We develop a checklist comprising objective and subjective queries to analyze behavior of large language models.<n>We propose metrics to assess factuality and fairness, and formally prove the inherent trade-off between these two aspects.
  arXiv  Detail & Related papers  (2025-02-09T10:54:11Z)
• GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models [3.018378575149671]
  We show that vision-language models (VLMs) are biased towards identifying the individual with the expected gender as the performer of the activity. We refer to this bias in associating an activity with the gender of its actual performer in an image or text as the Gender-Activity Binding (GAB) bias. Our experiments indicate that VLMs experience an average performance decline of about 13.2% when confronted with gender-activity binding bias.
  arXiv  Detail & Related papers  (2024-07-30T17:46:06Z)
• GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing [72.0343083866144]
  This paper introduces the GenderBias-emphVL benchmark to evaluate occupation-related gender bias in Large Vision-Language Models. Using our benchmark, we extensively evaluate 15 commonly used open-source LVLMs and state-of-the-art commercial APIs. Our findings reveal widespread gender biases in existing LVLMs.
  arXiv  Detail & Related papers  (2024-06-30T05:55:15Z)
• Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks [5.123567809055078]
  Gender bias in vision-language models (VLMs) can reinforce harmful stereotypes and discrimination. We propose GAMA, a task-agnostic generation framework to mitigate gender bias. During narrative generation, GAMA yields all-sided but gender-obfuscated narratives. During answer inference, GAMA integrates the image, generated narrative, and a task-specific question prompt to infer answers for different vision-language tasks.
  arXiv  Detail & Related papers  (2024-05-27T06:20:58Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• 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)
• UnQovering Stereotyping Biases via Underspecified Questions [68.81749777034409]
  We present UNQOVER, a framework to probe and quantify biases through underspecified questions. We show that a naive use of model scores can lead to incorrect bias estimates due to two forms of reasoning errors. We use this metric to analyze four important classes of stereotypes: gender, nationality, ethnicity, and religion.
  arXiv  Detail & Related papers  (2020-10-06T01:49:52Z)
• Grading video interviews with fairness considerations [1.7403133838762446]
  We present a methodology to automatically derive social skills of candidates based on their video response to interview questions. We develop two machine-learning models to predict social skills. We analyze fairness by studying the errors of models by race and gender.
  arXiv  Detail & Related papers  (2020-07-02T10:06:13Z)

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.