LAIBRE is a new Enterprise Ireland’s Co-Fund CareerFit-Plus Marie-Curie funded project that will end hiring discrimination.
A new Irish research project called LAIBRE is endeavouring to leverage artificial intelligence (AI) to remove any bias from the recruitment process helping to attract more diverse talent.
The project aims to eliminate bias across different Human Resources workflows with the help of advanced Natural Language Processing (NLP) techniques.
“Hiring bias occurs when candidates feel excluded or are considered positively or negatively because of certain characterisations which have nothing to do with their ability”
This project is expected to revolutionise the hiring process by providing equal career-building opportunities for candidates with diverse backgrounds.
The research will be conducted by innovator and data expert, Kolawole Adebayo, winner of the Marie-Curie CareerFit Plus Fellowship (Grant agreement No. 847402) with a budget of €259,550.
How hiring bias occurs
The work will be supervised by Professor Brian Davis of the School of Computing at DCU and the SFI ADAPT Centre. Kolawole will be working with industry partner, Datalive Analytics in Ireland, and the research and innovation centre, Learnovate to develop this project.
“Hiring bias occurs when candidates feel excluded or are considered positively or negatively because of certain characterisations which have nothing to do with their ability,” explained Adebayo.
“Hiring bias can lead to undue discrimination of quality candidates from the disadvantaged or minority groups such as women, people of colour, and those in the LGBTIQ community.
“LAIBRE seeks to overcome this by implementing AI models that can understand the contents of (human resource) HR documents to extract and remove information that can lead to unconscious bias and discrimination at the attraction and selection phases of hiring. For example at the job advertisement phase, LAIBRE will develop a domain adapted language model to aid the rewriting of inclusive job adverts; while at the candidate review phase, LAIBRE will implement a context-aware information extraction model to identify/remove protected attributes such as gender, ethnicity, etc. The project will implement models that learn intrinsic candidate suitability patterns from anonymized data for automated candidates review and selection towards skills-based hiring,” Adebayo added.
ADAPT is the world-leading SFI Research Centre for AI Driven Digital Content Technology led by Trinity College Dublin.
“Considering that recruiting is an economic gateway for many people to access job opportunities and earn income to support themselves and their families, the process needs to be fair and unbiased and factors like gender, ethnicity, or sexual orientation should not determine who gets hired or not,” said Prof Davis.
“Moreover, the issue can be viewed not just from the moral angle but also an economic one. Tackling bias in hiring will potentially reduce ‘bad hires’ while promoting diversity in workplaces which aside addressing an important equality issue also translates to more innovation, productivity, and profitability for employers. LAIBRE will contribute directly to the EU proposal for new regulations to guarantee excellence and trust in artificial intelligence.”