AI Bias in Resume Screening
Aliane Inès, Abidal Mauro · Team Bias_hiring
Submitted to Women in AI Safety Hackathon. Sprint projects are early-stage work by participants, not Apart Research publications.
Our project investigates gender bias in AI-driven resume screening using mechanistic interpretability techniques. By testing a language model's decision-making process on resumes differing only by gendered names, we uncovered a statistically significant bias favoring male-associated names in ambiguous cases. Using Goodfire’s Ember API, we analyzed model logits and performed rigorous statistical evaluations (t-tests, ANOVA, logistic regression).
Findings reveal that male names received more positive responses when skill matching was uncertain, highlighting potential discrimination risks in automated hiring systems. To address this, we propose mitigation strategies such as anonymization, fairness constraints, and continuous bias audits using interpretability tools. Our research underscores the importance of AI fairness and the need for transparent hiring practices in AI-powered recruitment.
This work contributes to AI safety by exposing and quantifying biases that could perpetuate systemic inequalities, urging the adoption of responsible AI development in hiring processes.
Reviews
Good idea - especially on IWD weekend! I like the mech interp approach to understanding model biases. As next steps, I'd recommend reading around the topic further - bias in AI is something that has been explored considerably previously and delving deep into the existing literature could help ground further work. Understanding AI bias has key implications on the AI safety space - I'd recommend testing the mitigation strategies and seeing how well they work; this would be a very valuable contribution to the field. It's also possible to extend this research to more demographic qualities like race. Great start and lots of scope for exciting further work!
Cite this project
@misc{ines2025ai,
title = {{AI Bias in Resume Screening}},
author = {Aliane Inès and Abidal Mauro},
year = {2025},
month = mar,
note = {Submitted to Women in AI Safety Hackathon, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/ai-bias-in-resume-screening}},
url = {https://apartresearch.com/sprints/projects/ai-bias-in-resume-screening}
}More from Women in AI Safety Hackathon
- Education track prizeView project: Morph: AI Safety Education Adaptable to (Almost) Anyone
Morph: AI Safety Education Adaptable to (Almost) Anyone
Morph
One-liner: Morph is the ultimate operation stack for AI safety education—combining dynamic localization, policy simulations, and ecosystem tools to turn abstract risks into actionable, culturally relevant solutions for …
- Mechanistic Interpretability PrizeView project: Red-teaming with Mech-Interpretability
Red-teaming with Mech-Interpretability
Red teaming large language models (LLMs) is crucial for identifying vulnerabilities before deployment, yet systematically creating effective adversarial prompts remains challenging. This project introduces a novel …
- Social Sciences track prizeView project: Detecting Malicious AI Agents Through Simulated Interactions
Detecting Malicious AI Agents Through Simulated Interactions
SafeAIGuard
This research investigates malicious AI Assistants’ manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making …