Towards Systematic Specification and Verification of Fairness Requirements: A Position Paper

2025-09-22

AI Summary

Existing algorithmic fairness research predominantly focuses on model or data bias, overlooking the root causes: the absence and unverifiability of fairness requirements. Domain experts’ fairness knowledge is often tacit and difficult to translate into precise, formally verifiable specifications. This project introduces the first knowledge graph–based framework for fairness engineering, systematically enabling explicit modeling, formal specification, and automated verification of fairness requirements. By integrating knowledge graphs, requirements engineering, and formal verification techniques, it supports fairness rule modeling, logical reasoning, and consistency checking. For the first time, it establishes a verifiable fairness assurance mechanism at the requirements level, identifies key technical challenges, and proposes viable methodological pathways. This work bridges a critical methodological gap in preventing algorithmic discrimination at its source and lays a foundation for building trustworthy AI systems.

Technology Category

• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness
• Knowledge Representation and Reasoning: Knowledge Engineering

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Responsible Web: Algorithmic accountability and transparency on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Decisions suggested by improperly designed software systems might be prone to discriminate against people based on protected characteristics, such as gender and ethnicity. Previous studies attribute such undesired behavior to flaws in algorithmic design or biased data. However, these studies ignore that discrimination is often the result of a lack of well-specified fairness requirements and their verification. The fact that experts' knowledge about fairness is often implicit makes the task of specifying precise and verifiable fairness requirements difficult. In related domains, such as security engineering, knowledge graphs have been proven to be effective in formalizing knowledge to assist requirements specification and verification. To address the lack of formal mechanisms for specifying and verifying fairness requirements, we propose the development of a knowledge graph-based framework for fairness. In this paper, we discuss the challenges, research questions, and a road map towards addressing the research questions.

Problem

• Addressing discrimination from software lacking formal fairness specifications
• Developing knowledge graph framework for verifiable fairness requirements
• Overcoming implicit fairness knowledge through systematic verification methods

Innovation

• Developing a knowledge graph-based framework for fairness
• Formalizing implicit fairness knowledge using knowledge graphs
• Assisting fairness requirements specification and verification systematically