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

arXiv: https://arxiv.org/abs/2603.08723 · HTML: https://mlsanity.com/paper/2603.08723/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Builds on (most cited first, 13 of 13)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Epistemic Injustice in Generative AI](https://mlsanity.com/paper/2408.11441/) (2024)
- [Evolution of Social Norms in LLM Agents using Natural Language](https://mlsanity.com/paper/2409.00993/) (2024)
- [Emergence of psychopathological computations in large language models](https://mlsanity.com/paper/2504.08016/) (2025)
- [ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems](https://mlsanity.com/paper/2602.08567/) (2026)
- [Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment](https://mlsanity.com/paper/2602.12134/) (2026)

## Built on by (most cited first, 2 of 2)

- [Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM Systems](https://mlsanity.com/paper/2605.13851/) (2026)
- [A Universal Cliff and a Design Fingerprint: Cross-Section Defect Detection Under LLM Orchestration](https://mlsanity.com/paper/2605.26174/) (2026)

## Abstract (arXiv)

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.