원문정보
초록
영어
Integrating Large Language Models (LLMs) into high-stakes evaluations like hiring and loans poses dual challenges: reducing algorithmic bias and embedding human compassion. We propose an AI evaluation framework grounded in the four-factor model of organizational justice, restructured into two dimensions: Structural Justice (procedural and distributive fairness) and Interactional Justice (interpersonal and informational compassion). Our modular, multi-agent system includes a Criteria Generator for fair rubric design and an Application Evaluator with two LLM agents—a “just bureaucrat” scoring structural fairness and a “compassionate communicator” scoring interactional fairness. These qualitative scores integrate with quantitative predictions through a Budget-Aware Fair Ranker to produce optimized outcomes. This framework offers a blueprint for AI systems that balance fairness with empathy, advancing beyond bias mitigation to foster just and compassionate decision-making in automated evaluations.
목차
1. Introduction
2. Theoretical Background: Organizational Justice “Four-Factor” Model
2.1 Systematic Justice: Distributive Justice and Procedural Justice
2.2 Interactional Justice: Interpersonal Justice and Informational Justice
3. Model Design
3.1 Criteria Generator
3.2 Application Evaluator
3.3 Budget-Aware Fair Ranker
4. Future Works
Acknowledgments
References