Multi-task adversarial learning detects intersectional algorithmic bias in AI recruitment systems.

AI / informaticsScientific reports· May 2026

Multi-task adversarial learning detects intersectional algorithmic bias in AI recruitment systems.

Jiwei Wang, Yan Xu, Ruifeng Liu, Yujiao Du

Read paper

AI Evaluation & GovernanceAI / informaticsQ1IF 5.0

New adversarial learning framework detects intersectional algorithmic bias more accurately than traditional methods.

Multi-task adversarial learning detects intersectional algorithmic bias in AI recruitment systems.

Jiwei Wang … Yujiao Du

Scientific reports · May 2026

Background

With the widespread application of artificial intelligence in recruitment, algorithmic bias issues have become increasingly prominent, seriously threatening social fairness and job seekers' rights.

12-18% points

Results

12-18% points

new method spots overlapping bias more reliably than older ones

“

Conclusion

Experimental results demonstrate that the framework improves intersectional bias detection accuracy by 12-18% points compared to traditional methods, providing effective technical support and theoretical guidance for fairness improvement in AI recruitment systems.

Multi-task adversarial learning detects intersectional algorithmic bias in AI recruitment systems.

Multi-task adversarial learning detects intersectional algorithmic bias in AI recruitment systems.

Related papers