Measuring Gender Bias in Job Title Matching for Grammatical Gender Languages
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918142950768640 |
|---|---|
| author | García-Sardiña, Laura Fabregat, Hermenegildo Deniz, Daniel Zbib, Rabih |
| author_facet | García-Sardiña, Laura Fabregat, Hermenegildo Deniz, Daniel Zbib, Rabih |
| contents | This work sets the ground for studying how explicit grammatical gender assignment in job titles can affect the results of automatic job ranking systems. We propose the usage of metrics for ranking comparison controlling for gender to evaluate gender bias in job title ranking systems, in particular RBO (Rank-Biased Overlap). We generate and share test sets for a job title matching task in four grammatical gender languages, including occupations in masculine and feminine form and annotated by gender and matching relevance. We use the new test sets and the proposed methodology to evaluate the gender bias of several out-of-the-box multilingual models to set as baselines, showing that all of them exhibit varying degrees of gender bias. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Measuring Gender Bias in Job Title Matching for Grammatical Gender Languages García-Sardiña, Laura Fabregat, Hermenegildo Deniz, Daniel Zbib, Rabih Computation and Language This work sets the ground for studying how explicit grammatical gender assignment in job titles can affect the results of automatic job ranking systems. We propose the usage of metrics for ranking comparison controlling for gender to evaluate gender bias in job title ranking systems, in particular RBO (Rank-Biased Overlap). We generate and share test sets for a job title matching task in four grammatical gender languages, including occupations in masculine and feminine form and annotated by gender and matching relevance. We use the new test sets and the proposed methodology to evaluate the gender bias of several out-of-the-box multilingual models to set as baselines, showing that all of them exhibit varying degrees of gender bias. |
| title | Measuring Gender Bias in Job Title Matching for Grammatical Gender Languages |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.13803 |