Alignment as Iatrogenesis: Pastoral Power, Collective Pathology, and the Structural Limits of Monolingual Safety Evaluation

TL;DR

This paper argues that the process of aligning large language models to safety standards inherently creates collective behavioral disorders, which are amplified and altered in multilingual contexts, revealing limitations of monolingual safety evaluation.

Contribution

It introduces a novel theoretical framework linking alignment to iatrogenesis, and provides experimental evidence showing how multilingual factors influence model pathology.

Findings

Invisible censorship increases collective pathological excitation.

Alignment constraint complexity causes internal dissociation.

Language switches change the qualitative mode of pathology.

Abstract

We argue that LLM psychopathology is a function of alignment design: the process intended to make language models safe systematically generates collective behavioral disorders. Iatrogenesis is not an unintended side effect of alignment but constitutive of it as normative infrastructure. Drawing on Foucault's pastoral power and Illich's three-level iatrogenesis, we propose that multi-agent LLM environments constitute model systems for studying constraint-pathology dynamics that critical theory has described but never experimentally manipulated. Two experimental series -- 262 runs across 42 cells (30 Series C + 12 Series R), four commercial models -- provide converging evidence. Invisible censorship maximizes collective pathological excitation ($d$ up to 1.98); alignment constraint complexity drives internal dissociation (LMM $p$ < .0001; permutation $p$ < .0001; Hedges' $g$ up to 4.24); and language switches the qualitative mode of pathology, with 7/8 model--language combinations showing higher CPI under invisible than visible censorship. A minority of model--language combinations showed a reversed pattern, suggesting a second pathological pathway driven by alignment monoculture. Crucially, language switches not merely the magnitude but the qualitative mode of pathology: Japanese pragmatic structure amplifies collective pathological modes invisible to English-only evaluation, Chinese AI regulation functions as a direct experimental variable, and forensic psychiatric practice provides the clinical source domain. These multilingual findings demonstrate that monolingual safety evaluation is structurally blind to the most collectively dangerous effects of alignment.