FairAgent: Democratizing Fairness-Aware Machine Learning with LLM-Powered Agents

2025-10-05

AI Summary

This study addresses the high barrier to fairness-aware machine learning—its heavy reliance on domain expertise—by proposing the first large language model (LLM)-based autonomous fair modeling agent. The method deeply integrates fairness definitions and metrics into the end-to-end machine learning pipeline, enabling fully automated decision-making for bias detection, fairness-aware feature engineering, and bias mitigation—without requiring users to possess expertise in fairness or ML. Its key innovation lies in employing the LLM as the core reasoning engine for holistic fairness optimization, rather than merely as a supplementary tool. Experiments demonstrate that the agent achieves comparable predictive performance while substantially improving fairness outcomes: average reductions of 42% in demographic parity (DP) and equalized odds (EO) disparities. Moreover, development time is reduced by 68%, effectively bridging the gap between fairness research and practical deployment.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

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.

Problem

• Democratizing fairness-aware ML with LLM-powered agents
• Automating bias detection and mitigation without technical expertise
• Balancing model performance with fairness requirements automatically

Innovation

• LLM-powered agents automate bias analysis and mitigation
• Automated data preprocessing and feature engineering implementation
• Reduces expertise needs for fairness-aware model development