Algorithmic Fairness: Not a Purely Technical but Socio-Technical Property

• URL: http://arxiv.org/abs/2506.12556v2
• Date: Thu, 18 Sep 2025 23:49:10 GMT
• Title: Algorithmic Fairness: Not a Purely Technical but Socio-Technical Property
• Authors: Yijun Bian, Lei You, Yuya Sasaki, Haruka Maeda, Akira Igarashi,
• Abstract summary: We argue that fairness cannot be reduced to purely technical constraints on models.<n>We examine the limitations of existing fairness measures through conceptual analysis and empirical illustrations.<n>We believe these findings will help bridge the gap between technical formalisation and social realities.
• Score: 4.2894701473635966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid trend of deploying artificial intelligence (AI) and machine learning (ML) systems in socially consequential domains has raised growing concerns about their trustworthiness, including potential discriminatory behaviours. Research in algorithmic fairness has generated a proliferation of mathematical definitions and metrics, yet persistent misconceptions and limitations -- both within and beyond the fairness community -- limit their effectiveness, such as an unreached consensus on its understanding, prevailing measures primarily tailored to binary group settings, and superficial handling for intersectional contexts. Here we critically remark on these misconceptions and argue that fairness cannot be reduced to purely technical constraints on models; we also examine the limitations of existing fairness measures through conceptual analysis and empirical illustrations, showing their limited applicability in the face of complex real-world scenarios, challenging prevailing views on the incompatibility between accuracy and fairness as well as that among fairness measures themselves, and outlining three worth-considering principles in the design of fairness measures. We believe these findings will help bridge the gap between technical formalisation and social realities and meet the challenges of real-world AI/ML deployment.

Related papers

• LTD-Bench: Evaluating Large Language Models by Letting Them Draw [57.237152905238084]
  LTD-Bench is a breakthrough benchmark for large language models (LLMs)<n>It transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code.<n> LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity.
  arXiv  Detail & Related papers  (2025-11-04T08:11:23Z)
• A Feminist Account of Intersectional Algorithmic Fairness [0.0]
  We propose Substantive Intersectional Algorithmic Fairness, extending Green's notion of substantive algorithmic fairness with insights from intersectional feminist theory.<n>We introduce ten desiderata within the ROOF methodology to guide the design, assessment, and deployment of algorithmic systems.<n>By bridging computational and social science perspectives, we provide actionable guidance for more equitable, inclusive, and context-sensitive intersectional algorithmic practices.
  arXiv  Detail & Related papers  (2025-08-25T12:09:04Z)
• MLLMs are Deeply Affected by Modality Bias [158.64371871084478]
  Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integrating diverse modalities such as texts and images.<n>MLLMs are heavily influenced by modality bias, often relying on language while under-utilizing other modalities like visual inputs.<n>This paper argues that MLLMs are deeply affected by modality bias, highlighting its manifestations across various tasks.
  arXiv  Detail & Related papers  (2025-05-24T11:49:31Z)
• The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation [73.16564415490113]
  Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant document from external knowledge sources.<n>We propose two approaches, FairFT and FairFilter, to mitigate the fairness issues introduced by RAG for small-scale LLMs.
  arXiv  Detail & Related papers  (2025-04-11T10:17:10Z)
• Contextual Fairness-Aware Practices in ML: A Cost-Effective Empirical Evaluation [48.943054662940916]
  We investigate fairness-aware practices from two perspectives: contextual and cost-effectiveness.<n>Our findings provide insights into how context influences the effectiveness of fairness-aware practices.<n>This research aims to guide SE practitioners in selecting practices that achieve fairness with minimal performance costs.
  arXiv  Detail & Related papers  (2025-03-19T18:10:21Z)
• Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models [91.24296813969003]
  This paper advocates integrating causal methods into machine learning to navigate the trade-offs among key principles of trustworthy ML.<n>We argue that a causal approach is essential for balancing multiple competing objectives in both trustworthy ML and foundation models.
  arXiv  Detail & Related papers  (2025-02-28T14:57:33Z)
• Perceived Fairness of the Machine Learning Development Process: Concept Scale Development [0.0]
  unfairness is triggered due to bias in the data, the data curation process, erroneous assumptions, and implicit bias rendered during the development process.<n>We propose operational attributes of perceived fairness to be transparency, accountability, and representativeness.<n>The multidimensional framework for perceived fairness offers a comprehensive understanding of perceived fairness.
  arXiv  Detail & Related papers  (2025-01-23T06:51:31Z)
• The Impossibility of Fair LLMs [17.812295963158714]
  We analyze a variety of technical fairness frameworks and find inherent challenges in each that make the development of a fair language model intractable.<n>We show that each framework either does not extend to the general-purpose AI context or is infeasible in practice.<n>These inherent challenges would persist for general-purpose AI, including LLMs, even if empirical challenges, such as limited participatory input and limited measurement methods, were overcome.
  arXiv  Detail & Related papers  (2024-05-28T04:36:15Z)
• Parametric Fairness with Statistical Guarantees [0.46040036610482665]
  We extend the concept of Demographic Parity to incorporate distributional properties in predictions, allowing expert knowledge to be used in the fair solution. We illustrate the use of this new metric through a practical example of wages, and develop a parametric method that efficiently addresses practical challenges.
  arXiv  Detail & Related papers  (2023-10-31T14:52:39Z)
• Reconciling Predictive and Statistical Parity: A Causal Approach [68.59381759875734]
  We propose a new causal decomposition formula for the fairness measures associated with predictive parity. We show that the notions of statistical and predictive parity are not really mutually exclusive, but complementary and spanning a spectrum of fairness notions.
  arXiv  Detail & Related papers  (2023-06-08T09:23:22Z)
• Individual Fairness under Uncertainty [26.183244654397477]
  Algorithmic fairness is an established area in machine learning (ML) algorithms. We propose an individual fairness measure and a corresponding algorithm that deal with the challenges of uncertainty arising from censorship in class labels. We argue that this perspective represents a more realistic model of fairness research for real-world application deployment.
  arXiv  Detail & Related papers  (2023-02-16T01:07:58Z)
• Fairness in Matching under Uncertainty [78.39459690570531]
  algorithmic two-sided marketplaces have drawn attention to the issue of fairness in such settings. We axiomatize a notion of individual fairness in the two-sided marketplace setting which respects the uncertainty in the merits. We design a linear programming framework to find fair utility-maximizing distributions over allocations.
  arXiv  Detail & Related papers  (2023-02-08T00:30:32Z)
• Fair Decision-making Under Uncertainty [1.5688552250473473]
  We study a longitudinal censored learning problem subject to fairness constraints. We show how the newly devised fairness notions involving censored information and the general framework for fair predictions in the presence of censorship allow us to measure and discrimination under uncertainty.
  arXiv  Detail & Related papers  (2023-01-29T05:42:39Z)
• Tensions Between the Proxies of Human Values in AI [20.303537771118048]
  We argue that the AI community needs to consider all the consequences of choosing certain formulations of these pillars. We point towards sociotechnical research for frameworks for the latter, but push for broader efforts into implementing these in practice.
  arXiv  Detail & Related papers  (2022-12-14T21:13:48Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing [62.9062883851246]
  Machine learning holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. One potential driver of algorithmic unfairness, shortcut learning, arises when ML models base predictions on improper correlations in the training data. Using multi-task learning, we propose the first method to assess and mitigate shortcut learning as a part of the fairness assessment of clinical ML systems.
  arXiv  Detail & Related papers  (2022-07-21T09:35:38Z)
• Fair Machine Learning in Healthcare: A Review [90.22219142430146]
  We analyze the intersection of fairness in machine learning and healthcare disparities. We provide a critical review of the associated fairness metrics from a machine learning standpoint. We propose several new research directions that hold promise for developing ethical and equitable ML applications in healthcare.
  arXiv  Detail & Related papers  (2022-06-29T04:32:10Z)
• What Is Fairness? On the Role of Protected Attributes and Fictitious Worlds [8.223468651994352]
  A growing body of literature in fairness-aware machine learning (fairML) aims to mitigate machine learning (ML)-related unfairness in automated decision-making (ADM)<n>However, the underlying concept of fairness is rarely discussed, leaving a significant gap between centuries of philosophical discussion and the recent adoption of the concept in the ML community.<n>We try to bridge this gap by formalizing a consistent concept of fairness and by translating the philosophical considerations into a formal framework for the training and evaluation of ML models in ADM systems.
  arXiv  Detail & Related papers  (2022-05-19T15:37:26Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)
• Fairness in Machine Learning [15.934879442202785]
  We show how causal Bayesian networks can play an important role to reason about and deal with fairness. We present a unified framework that encompasses methods that can deal with different settings and fairness criteria.
  arXiv  Detail & Related papers  (2020-12-31T18:38:58Z)
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty [66.17147341354577]
  We argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. We describe how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness.
  arXiv  Detail & Related papers  (2020-11-15T17:26:14Z)
• Participatory Problem Formulation for Fairer Machine Learning Through Community Based System Dynamics [0.0]
  The problem formulation phase of ML system development can be a key source of bias that has significant downstream impacts on ML system fairness outcomes. Current practice neither accounts for the dynamic complexity of high-stakes domains nor incorporates the perspectives of vulnerable stakeholders. We introduce community based system dynamics (CBSD) as an approach to enable the participation of typically excluded stakeholders in the problem formulation phase of the ML system development process.
  arXiv  Detail & Related papers  (2020-05-15T14:41:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.