The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918041343754240 |
|---|---|
| author | Kamruzzaman, Mahammed Kim, Gene Louis |
| author_facet | Kamruzzaman, Mahammed Kim, Gene Louis |
| contents | As large language models (LLMs) become increasingly integrated into hiring processes, concerns about fairness have gained prominence. When applying for jobs, companies often request/require demographic information, including gender, race, and disability or veteran status. This data is collected to support diversity and inclusion initiatives, but when provided to LLMs, especially disability-related information, it raises concerns about potential biases in candidate selection outcomes. Many studies have highlighted how disability can impact CV screening, yet little research has explored the specific effect of voluntarily disclosed information on LLM-driven candidate selection. This study seeks to bridge that gap. When candidates shared identical gender, race, qualifications, experience, and backgrounds, and sought jobs with minimal employment rate gaps between individuals with and without disabilities (e.g., Cashier, Software Developer), LLMs consistently favored candidates who disclosed that they had no disability. Even in cases where candidates chose not to disclose their disability status, the LLMs were less likely to select them compared to those who explicitly stated they did not have a disability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00256 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selection Kamruzzaman, Mahammed Kim, Gene Louis Computation and Language As large language models (LLMs) become increasingly integrated into hiring processes, concerns about fairness have gained prominence. When applying for jobs, companies often request/require demographic information, including gender, race, and disability or veteran status. This data is collected to support diversity and inclusion initiatives, but when provided to LLMs, especially disability-related information, it raises concerns about potential biases in candidate selection outcomes. Many studies have highlighted how disability can impact CV screening, yet little research has explored the specific effect of voluntarily disclosed information on LLM-driven candidate selection. This study seeks to bridge that gap. When candidates shared identical gender, race, qualifications, experience, and backgrounds, and sought jobs with minimal employment rate gaps between individuals with and without disabilities (e.g., Cashier, Software Developer), LLMs consistently favored candidates who disclosed that they had no disability. Even in cases where candidates chose not to disclose their disability status, the LLMs were less likely to select them compared to those who explicitly stated they did not have a disability. |
| title | The Impact of Disability Disclosure on Fairness and Bias in LLM-Driven Candidate Selection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.00256 |