FairAgent: Democratizing Fairness-Aware Machine Learning with LLM-Powered Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916990892900352 |
|---|---|
| author | Dai, Yucong Zhang, Lu Luo, Feng Chowdhury, Mashrur Wu, Yongkai |
| author_facet | Dai, Yucong Zhang, Lu Luo, Feng Chowdhury, Mashrur Wu, Yongkai |
| contents | Training fair and unbiased machine learning models is crucial for high-stakes applications, yet it presents significant challenges. Effective bias mitigation requires deep expertise in fairness definitions, metrics, data preprocessing, and machine learning techniques. In addition, the complex process of balancing model performance with fairness requirements while properly handling sensitive attributes makes fairness-aware model development inaccessible to many practitioners. To address these challenges, we introduce FairAgent, an LLM-powered automated system that significantly simplifies fairness-aware model development. FairAgent eliminates the need for deep technical expertise by automatically analyzing datasets for potential biases, handling data preprocessing and feature engineering, and implementing appropriate bias mitigation strategies based on user requirements. Our experiments demonstrate that FairAgent achieves significant performance improvements while significantly reducing development time and expertise requirements, making fairness-aware machine learning more accessible to practitioners. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04317 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FairAgent: Democratizing Fairness-Aware Machine Learning with LLM-Powered Agents Dai, Yucong Zhang, Lu Luo, Feng Chowdhury, Mashrur Wu, Yongkai Machine Learning Artificial Intelligence Training fair and unbiased machine learning models is crucial for high-stakes applications, yet it presents significant challenges. Effective bias mitigation requires deep expertise in fairness definitions, metrics, data preprocessing, and machine learning techniques. In addition, the complex process of balancing model performance with fairness requirements while properly handling sensitive attributes makes fairness-aware model development inaccessible to many practitioners. To address these challenges, we introduce FairAgent, an LLM-powered automated system that significantly simplifies fairness-aware model development. FairAgent eliminates the need for deep technical expertise by automatically analyzing datasets for potential biases, handling data preprocessing and feature engineering, and implementing appropriate bias mitigation strategies based on user requirements. Our experiments demonstrate that FairAgent achieves significant performance improvements while significantly reducing development time and expertise requirements, making fairness-aware machine learning more accessible to practitioners. |
| title | FairAgent: Democratizing Fairness-Aware Machine Learning with LLM-Powered Agents |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04317 |