Jul 2026· Science and Engineering Ethics· 0 citations
TL;DR
The paper’s central argumentative shift is to change the narrative from bias mitigation to bias management—treating bias not as a defect to be corrected but as an ongoing condition to be governed.
Abstract
Dominant approaches to bias in artificial intelligence (AI) are structured by what I identify as the isolationist problem: the tendency to treat bias as a discrete, technically addressable flaw within the AI development pipeline, rather than as a relational phenomenon embedded in social, institutional, and political arrangements. This problem is sustained by two mutually reinforcing orientations: technocentrism, which reframes ethical challenges as engineering problems amenable to computational resolution, and the bias-centric conception of fairness, which reduces fairness to statistical mitigation and obscures its contested, context-dependent character. Together, these orientations produce ontological, epistemic, and practical forms of narrowing ethical imagination and channel intervention into technically tractable but socially limited responses. Against this, I propose sociotechnical sensitivity as both an analytical orientation and a normative commitment: a sustained attentiveness to the ways in which AI systems are constitutively embedded in social relations, institutional arrangements, cultural norms, and power structures. The paper’s central argumentative shift is to change the narrative from bias mitigation to bias management—treating bias not as a defect to be corrected but as an ongoing condition to be governed. These arguments are developed through an extended analysis of the well-known case of the COMPAS algorithm, a recidivism risk-assessment prediction tool, illustrating three practical axes of bias management: contextualisation, institutionalisation, and iteration. The gap between sociotechnically sensitive AI ethics and its realisation is ultimately a matter of governance design and political will, not merely a problem of missing methods or tools.
This paper argues that the dominant anthropomorphism frame operates from a position of institutional advantage rather than earned epistemic authority: collapsing the variety of academic perspectives into a single outbound position of user error, imposed without establishing the grounds required to justify it and without accounting for the harms it produces.
LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed. This inconsistency is a problem for any system whose outputs are used to inform moral decisions. If generative systems exhibit internal inconsistency, then the epistemic integrity of AI-mediated systems becomes uncertain. To study this concern, we investigate the stability of moral reasoning in LLMs within a controlled prompting framework across three major philosophical schools of thought: deontology, utilitarianism, and virtue ethics. We construct sets of morally equivalent scenarios in which the underlying situation is held constant while the framing varies to reflect different ethical stances and stylistic perturbations. We then evaluate responses from multiple models, including GPT, Mistral, and Llama. To assess consistency, we convert model outputs into structured logical statements and identify contradictions across responses generated within the same school of thought. Our results reveal substantial inconsistency with contradiction rates reaching up to 78% across scenarios. These findings point to a broader phenomenon of epistemic instability in generative AI wherein models fail to reliably maintain coherence with respect to their own prior outputs. This kind of instability carries real consequences. As generative systems influence how people form beliefs, judge actions, and absorb values, their inconsistencies can shape human reasoning and decision-making as well. Moreover, if a system cannot consistently represent its own normative commitments, then value alignment becomes a moving target rather than a well-defined objective. Thus, we argue that demonstrating internal incoherence is a necessary precursor to AI alignment.
Pegah Nokhiz, Aravinda Kanchana Ruwanpathirana, Helen Nissenbaum· 0 citations
The argument further holds that AI does not possess moral agency in the classical sense but functions as an infrastructural precondition for the reconfiguration of normative hierarchies—in an empirical rather than transcendental sense.
Political science is undergoing a pronounced methodological shift toward causal identification and design-based inference, increasingly marginalizing qualitative and observational approaches. We argue that this shift rests on the flawed premise that methods can be ranked in the abstract, independently of the research question and the theories at stake. Drawing on a Popperian understanding of scientific progress, we develop a framework of comparative theory testing in which method choice is derived from the competing theories themselves. When rival theories generate observationally non-equivalent implications—causal, correlational, or descriptive—any form of evidence capable of adjudicating between them has epistemic standing. This grounds methodological pluralism not in a normative appeal for inclusivity, but in the internal logic of rigorous theory testing. We illustrate the framework through canonical examples, propose criteria for evaluating the rigor of comparative theory tests, and show that design-based methods earn their place within—not above—this framework. The result is a unified perspective that preserves our capacity to engage big-picture questions while maintaining the standards of falsifiability and theoretical precision that scientific inquiry requires.
H. Bulutgil, Harris Mylonas· International Political Scie...· 1 citation
Social psychology presents itself as liberal, yet its dominant narratives-obedience, cruelty, conformity, and bias-reflect a persistently pessimistic portrayal of human nature. Here I argue that this pattern is structurally produced. A two-level framework distinguishes the content level, in which pessimistic narratives circulate, from the structural level, in which incentive regimes in academic publishing, media, and pedagogy systematically select and stabilize that content. Two mechanisms are identified. A market-selection mechanism explains why attention economies favor dramatic, morally arousing findings. An institutional-stabilization mechanism explains why pessimistic narratives prove especially durable: They participate in the constitutive logic of the "psy-complex," in which psychological expertise gains authority by rendering human conduct legible as a problem requiring expert correction. Findings that portray ordinary people as biased, obedient, or morally fragile are apt to generate the remediation apparatus on which the field's social legitimacy depends. Archival evidence shows that classic studies were staged and selectively framed to produce pessimistic morals. The replication crisis retroactively identified much of this content as incentive-compatible rather than epistemically robust. Reform efforts (e.g., registered reports, open data, equity-oriented partnerships) can address the market-selection side; changing the institutional-stabilization dynamic requires reflexive attention to whose interests a deficit-focused discipline serves.
Jan-Erik Lönnqvist· Perspectives on Psychologica...· 0 citations
It is argued that current benchmarking practices may perpetuate systematic harms affecting various actors in AI research, aligning with four of Iris Marion Young's theories of oppression and structural injustice.