# Bias in Multimodal AI: Testbed for Fair Automatic Recruitment

arXiv: https://arxiv.org/abs/2004.07173 · HTML: https://mlsanity.com/paper/2004.07173/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2020.

## Built on by (most cited first, 21 of 21)

- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [A Review on Explainability in Multimodal Deep Neural Nets](https://mlsanity.com/paper/2105.07878/) (2021)
- [Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment](https://mlsanity.com/paper/2302.10908/) (2023)
- [Identifying and Improving Disability Bias in GPT-Based Resume Screening](https://mlsanity.com/paper/2402.01732/) (2024)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics](https://mlsanity.com/paper/2307.03195/) (2023)
- [Balancing Biases and Preserving Privacy on Balanced Faces in the Wild](https://mlsanity.com/paper/2103.09118/) (2021)
- [A Survey on Safe Multi-Modal Learning System](https://mlsanity.com/paper/2402.05355/) (2024)
- [Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment](https://mlsanity.com/paper/2506.11880/) (2025)
- [PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)](https://mlsanity.com/paper/2507.02966/) (2025)
- [A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future](https://mlsanity.com/paper/2412.14056/) (2024)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [Interrogating AI: Characterizing Emergent Playful Interactions with ChatGPT](https://mlsanity.com/paper/2401.08405/) (2024)
- ["I'm Not Confident in Debiasing AI Systems Since I Know Too Little": Teaching AI Creators About Gender Bias Through Hands-on Tutorials](https://mlsanity.com/paper/2309.08121/) (2023)
- [Exploring Fusion Techniques in Multimodal AI-Based Recruitment: Insights from FairCVdb](https://mlsanity.com/paper/2407.16892/) (2024)
- [FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations](https://mlsanity.com/paper/2412.07313/) (2024)
- [Behind the Screens: Uncovering Bias in AI-Driven Video Interview Assessments Using Counterfactuals](https://mlsanity.com/paper/2505.12114/) (2025)
- [Synthetic CVs To Build and Test Fairness-Aware Hiring Tools](https://mlsanity.com/paper/2508.21179/) (2025)
- [More is Less? A Simulation-Based Approach to Dynamic Interactions between Biases in Multimodal Models](https://mlsanity.com/paper/2412.17505/) (2024)
- [Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment](https://mlsanity.com/paper/2607.20073/) (2026)

## Abstract (arXiv)

The presence of decision-making algorithms in society is rapidly increasing nowadays, while concerns about their transparency and the possibility of these algorithms becoming new sources of discrimination are arising. In fact, many relevant automated systems have been shown to make decisions based on sensitive information or discriminate certain social groups (e.g. certain biometric systems for person recognition). With the aim of studying how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data, we propose a fictitious automated recruitment testbed: FairCVtest. We train automatic recruitment algorithms using a set of multimodal synthetic profiles consciously scored with gender and racial biases. FairCVtest shows the capacity of the Artificial Intelligence (AI) behind such recruitment tool to extract sensitive information from unstructured data, and exploit it in combination to data biases in undesirable (unfair) ways. Finally, we present a list of recent works developing techniques capable of removing sensitive information from the decision-making process of deep learning architectures. We have used one of these algorithms (SensitiveNets) to experiment discrimination-aware learning for the elimination of sensitive information in our multimodal AI framework. Our methodology and results show how to generate fairer AI-based tools in general, and in particular fairer automated recruitment systems.