Demographic Fairness in Multimodal LLMs: A Benchmark of Gender and Ethnicity Bias in Face Verification

• URL: http://arxiv.org/abs/2603.25613v1
• Date: Thu, 26 Mar 2026 16:30:00 GMT
• Title: Demographic Fairness in Multimodal LLMs: A Benchmark of Gender and Ethnicity Bias in Face Verification
• Abstract summary: Multimodal Large Language Models (MLLMs) have been explored as face verification systems.<n>We present a benchmarking study that evaluates nine open-source MLLMs from six model families.<n>Our results show that FaceLLM-8B, the only face-specialised model in our study, substantially outperforms general-purpose MLLMs on both benchmarks.
• Score: 39.17203445317177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) have recently been explored as face verification systems that determine whether two face images are of the same person. Unlike dedicated face recognition systems, MLLMs approach this task through visual prompting and rely on general visual and reasoning abilities. However, the demographic fairness of these models remains largely unexplored. In this paper, we present a benchmarking study that evaluates nine open-source MLLMs from six model families, ranging from 2B to 8B parameters, on the IJB-C and RFW face verification protocols across four ethnicity groups and two gender groups. We measure verification accuracy with the Equal Error Rate and True Match Rate at multiple operating points per demographic group, and we quantify demographic disparity with four FMR-based fairness metrics. Our results show that FaceLLM-8B, the only face-specialised model in our study, substantially outperforms general-purpose MLLMs on both benchmarks. The bias patterns we observe differ from those commonly reported for traditional face recognition, with different groups being most affected depending on the benchmark and the model. We also note that the most accurate models are not necessarily the fairest and that models with poor overall accuracy can appear fair simply because they produce uniformly high error rates across all demographic groups.

Related papers

• Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos [79.03150233804458]
  Real-world images entangle race and gender with correlated factors such as background and clothing, obscuring attribution.<n>We propose a textbfface-only counterfactual evaluation paradigm<n>We generate counterfactual variants by editing only facial attributes related to race and gender, keeping all other visual factors fixed.
  arXiv  Detail & Related papers  (2026-01-11T14:35:06Z)
• Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs [65.93003087656754]
  VisFactor is a benchmark that digitizes 20 vision-centric subtests from a well-established cognitive psychology assessment.<n>We evaluate 20 frontier Multimodal Large Language Models (MLLMs) from GPT, Gemini, Claude, LLaMA, Qwen, and SEED families.<n>The best-performing model achieves a score of only 25.19 out of 100, with consistent failures on tasks such as mental rotation, spatial relation inference, and figure-ground discrimination.
  arXiv  Detail & Related papers  (2025-02-23T04:21:32Z)
• Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts [19.20592062296075]
  Large language models (LLMs) are increasingly being deployed in high-stakes applications like hiring.<n>This work examines the allocational fairness of LLM-based hiring systems through two tasks that reflect actual HR usage.
  arXiv  Detail & Related papers  (2025-01-08T07:28:10Z)
• 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)
• Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models [10.73340009530019]
  This study addresses two such biases within Large Language Models (LLMs): representative bias and affinity bias. We introduce two novel metrics to measure these biases: the Representative Bias Score (RBS) and the Affinity Bias Score (ABS) Our analysis uncovers marked representative biases in prominent LLMs, with a preference for identities associated with being white, straight, and men. Our investigation of affinity bias reveals distinctive evaluative patterns within each model, akin to bias fingerprints'
  arXiv  Detail & Related papers  (2024-05-23T13:35:34Z)
• Social Bias Probing: Fairness Benchmarking for Language Models [38.180696489079985]
  This paper proposes a novel framework for probing language models for social biases by assessing disparate treatment. We curate SoFa, a large-scale benchmark designed to address the limitations of existing fairness collections. We show that biases within language models are more nuanced than acknowledged, indicating a broader scope of encoded biases than previously recognized.
  arXiv  Detail & Related papers  (2023-11-15T16:35:59Z)
• DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision [73.80009454050858]
  This work presents a self-supervised model, called DualFair, that can debias sensitive attributes like gender and race from learned representations. Our model jointly optimize for two fairness criteria - group fairness and counterfactual fairness.
  arXiv  Detail & Related papers  (2023-03-15T07:13:54Z)
• Towards Explaining Demographic Bias through the Eyes of Face Recognition Models [6.889667606945215]
  Biases inherent in both data and algorithms make the fairness of machine learning (ML)-based decision-making systems less than optimal. We aim at providing a set of explainability tool that analyse the difference in the face recognition models' behaviors when processing different demographic groups. We do that by leveraging higher-order statistical information based on activation maps to build explainability tools that link the FR models' behavior differences to certain facial regions.
  arXiv  Detail & Related papers  (2022-08-29T07:23:06Z)
• Are Commercial Face Detection Models as Biased as Academic Models? [64.71318433419636]
  We compare academic and commercial face detection systems, specifically examining robustness to noise. We find that state-of-the-art academic face detection models exhibit demographic disparities in their noise robustness. We conclude that commercial models are always as biased or more biased than an academic model.
  arXiv  Detail & Related papers  (2022-01-25T02:21:42Z)
• Mitigating Face Recognition Bias via Group Adaptive Classifier [53.15616844833305]
  This work aims to learn a fair face representation, where faces of every group could be more equally represented. Our work is able to mitigate face recognition bias across demographic groups while maintaining the competitive accuracy.
  arXiv  Detail & Related papers  (2020-06-13T06:43:37Z)

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.