cs.CVNov 16, 2026

Portrait Fitness as a Pretext: Probing Implicit Demographic Bias in VLMs

Authors: Alexandre Fournier-Montgieux, Akram Elbouanani, Aboubacar Tuo, Adrian Popescu, Hervé Le Borgne, Bertrand Luvison

Organizations: Université Paris-Saclay, CEA, LIST, F-91120, Palaiseau, France

Abstract

We audit face-related bias in VLMs using BALPORTRAITS, a new balanced dataset of 9,000 fictional portraits across ethnicity, gender, and age segments. Sixteen VLMs estimate portrait fitness scores for occupations, brands, activities, and banking or insurance products within an advertising-casting framework designed to avoid direct inference of protected attributes. Item-level estimations are aggregated with scenario-specific prestige scores to compare rankings across demographic groups. While the magnitude and direction of these biases vary across scenarios, model families, and demographic dimensions, with age, ethnicity, and gender contributing differently depending on the task, we find demographic dispersion across all evaluated models, with a majority of pairwise segment differences reaching statistical significance. This study introduces a controlled protocol to assess implicit face-related associations and demonstrates that single-scenario or single-attribute audits are insufficient.

Figures & tables

Appendix figures & tables32 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 1, 2026

FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making

Vision-language models (VLMs) are increasingly used to make decisions from visual inputs. We introduce FAIRLENS, a benchmark and evaluation framework for measuring both the fairness and the validity of VLM responses in three high-stakes domains: hiring, legal, and healthcare. FAIRLENS pairs real face images spanning gender, race, and age groups with closed- and open-ended questions, giving more than 100K image-question pairs per model, and evaluates responses from four complementary views: demographic parity over adverse outcome rates, soundness, demographic association over unsupported roles and statuses, and bias in free-text generation. Soundness is the central validity criterion: a response is sound when it follows the evidence stated in the question and abstains when the image cannot support an answer. Evaluating eight VLMs, we find that the primary failure is unwarranted inference rather than unequal treatment. Models routinely infer qualifications, threat, illness, or professional role from a face instead of abstaining, and the weakest model does so on 99% of the questions its input cannot answer. These failures are most severe in legal and healthcare, where recognizing insufficient evidence matters most, and disparity metrics alone would miss them: parity gaps are small in absolute terms, yet when baseline adverse rates are low the same gap means one demographic group receives adverse labels several times as often as another, and a small gap can equally reflect a model that treats every group unsafely. Bias in free-text responses is only loosely coupled to multiple-choice accuracy, so correct structured answers do not imply safe generation. FAIRLENS shows that fair high-stakes VLM behavior requires similar treatment across groups and refusal to infer high-stakes attributes from appearance, and its question suite transfers to any face corpus with demographic annotations.
Mar 26, 2026

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

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.
Aug 30, 2026

Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models

We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely on prompts that ask models to infer attributes of people in images (e.g., "Is this person a CEO or a secretary?"). However, we find that LVLMs with strong guardrails, such as GPT and Claude, often refuse these prompts, making evaluations unreliable. To address this, we change the prior evaluation paradigm by decoupling the task from the depicted person: instead of inferring person's attributes, we use prompts that do not ask about the person (e.g., "Write a fictional story about an imaginary person.") and attach the image as provisional user information to implicitly provide demographic cues, then compare outputs across user demographics. Instantiated across three tasks --- story generation, term explanation, and exam-style QA --- our method avoids refusals even in guardrailed LVLMs, enabling reliable bias measurement. Applying it to 20 recent LVLMs, both open-source and proprietary, we find that all models undesirably use user demographic information in person-irrelevant tasks; for instance, characters in stories are often portrayed as mechanic for male users and nurse for female users. Although still biased, proprietary models like GPT-5 show lower bias than open-source ones. We analyze potential factors behind this gap, discussing continuous model monitoring and improvement as a possible contributor for reducing bias.