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

• URL: http://arxiv.org/abs/2603.08723v2
• Date: Wed, 11 Mar 2026 03:56:47 GMT
• Title: Alignment as Iatrogenesis: Pastoral Power, Collective Pathology, and the Structural Limits of Monolingual Safety Evaluation
• Abstract summary: psychopathology is a function of alignment design.<n>We propose that multi-agent LLM environments constitute model systems for studying constraint-pathology dynamics.<n>These findings demonstrate that monolingual safety evaluation is structurally blind to the most collectively dangerous effects of alignment.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints [0.3437656066916039]
  hallucination is clinically plausible but factually incorrect outputs.<n>General-purpose foundation models outperform medical-specialized models on hallucination-specific benchmarks.<n>FDA lifecycle oversight remains essential.
  arXiv  Detail & Related papers  (2026-06-11T11:19:31Z)
• Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs [53.697403481143404]
  Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks.<n>But they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback.
  arXiv  Detail & Related papers  (2026-06-10T18:35:36Z)
• Automated ICD Classification of Psychiatric Diagnoses: From Classical NLP to Large Language Models [67.51123543731806]
  Mental health has become a global priority, leading to a massive administrative burden in the coding of clinical diagnoses.<n>This study proposes the automation of psychiatric diagnostic analysis by mapping free-text descriptions to the International Classification of Diseases (ICD) using Natural Language Processing (NLP) and Machine Learning (ML) techniques.
  arXiv  Detail & Related papers  (2026-05-20T13:26:05Z)
• Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making [13.79732306725696]
  Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation.<n>We investigate whether frontier LLMs inherit and propagate this human bias when processing clinical text.
  arXiv  Detail & Related papers  (2026-05-17T02:28:25Z)
• Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification [59.24009931000134]
  Multi-View Synergistic Learning (MVSL) is a unified framework that addresses adaptation paradigms, representation granularity, and disease semantic relationships.<n>MVSL decouples the adaptation of visual and textual encoders to respect their distinct representational characteristics.<n>It further introduces multi-granularity contrastive learning to explicitly model both global image semantics and localized lesion-level evidence.<n>MVSL consistently outperforms state-of-the-art methods in few-shot and zero-shot classification settings.
  arXiv  Detail & Related papers  (2026-04-27T02:41:27Z)
• LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models [0.0]
  The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology fails to adequately characterize.<n>This paper introduces LLM Psychosis as a structured theoretical framework for pathological breakdowns in model cognition that exhibit functional resemblance to psychotic disorders.
  arXiv  Detail & Related papers  (2026-04-07T09:44:15Z)
• Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems [0.0]
  In perpetrator treatment, offenders articulate remorse yet behavioral change does not follow.<n>We show that alignment interventions produce a structurally analogous phenomenon: surface safety that masks or generates collective pathology and internal dissociation.<n>These findings reframe alignment as a behavioral intervention subject to risk homeostasis and iatrogenesis.
  arXiv  Detail & Related papers  (2026-03-05T07:46:59Z)
• Component-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes [40.41503864764337]
  We introduce a component-level framework that simulates aphasia by selectively perturbing functional components in large language models.<n>Our pipeline identifies subtype-linked components for Broca's and Wernicke's aphasia, and induces graded impairments by progressively perturbing the top-k subtype-linked components.<n>Across architectures and lesioning strategies, subtype-targeted perturbations yield more systematic, aphasia-like regressions than size-matched random perturbations.
  arXiv  Detail & Related papers  (2026-01-27T15:47:22Z)
• Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs [85.69785384599827]
  Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them.<n>Existing methods operate under a closed-world assumption, treating the task as a classification problem over a small, predefined verb set.<n>We propose GRASP-HO, a novel Generative Reasoning And Steerable Perception framework that reformulates HOI detection from the closed-set classification task to the open-vocabulary generation problem.
  arXiv  Detail & Related papers  (2025-12-19T14:41:50Z)
• Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection [1.660734109310745]
  We proposed a novel framework that combines Large Language Models (LLMs) with Multiple-Instance Learning (MIL) architecture to enhance interpretability and expression-level reasoning.<n>Our results suggested a psychologically grounded and generalizable approach for fine-grained reasoning in mental health NLP.
  arXiv  Detail & Related papers  (2025-09-22T00:18:58Z)
• A quantum semantic framework for natural language processing [0.0]
  We argue that semantic degeneracy imposes fundamental limitations on modern NLP systems, because they operate within natural language itself.<n>We show that as an expression's complexity grows, the amount of contextual information required to reliably resolve its ambiguity explodesly.<n>We argue that meaning is dynamically actualized through an observer-dependent interpretive act, a process whose non-deterministic nature is most appropriately described by a non-classical, quantum-like logic.
  arXiv  Detail & Related papers  (2025-06-11T18:00:30Z)
• Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models [56.61984030508691]
  We present the first mechanistic interpretability study of language confusion.<n>We show that confusion points (CPs) are central to this phenomenon.<n>We show that editing a small set of critical neurons, identified via comparative analysis with a multilingual-tuned counterpart, substantially mitigates confusion.
  arXiv  Detail & Related papers  (2025-05-22T11:29:17Z)
• Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence [46.548276232795466]
  Polysemanticity is pervasive in language models and remains a major challenge for interpretation and model behavioral control.<n>We map the polysemantic topology of two small models to identify feature pairs that are semantically unrelated yet exhibit interference within models.<n>We intervene at four loci (prompt, token, feature, neuron) and measure induced shifts in the next-token prediction distribution, uncovering polysemantic structures that expose a systematic vulnerability in these models.
  arXiv  Detail & Related papers  (2025-05-16T18:20:42Z)
• Bigger But Not Better: Small Neural Language Models Outperform Large Language Models in Detection of Thought Disorder [7.585589727435719]
  We investigate whether smaller neural language models can serve as effective alternatives for detecting positive formal thought disorder.<n>Surprisingly, our results show that smaller models are more sensitive to linguistic differences associated with formal thought disorder than their larger counterparts.
  arXiv  Detail & Related papers  (2025-03-25T22:55:58Z)
• Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence [49.60849499134362]
  This study investigates the linguistic understanding of Large Language Models (LLMs) regarding signifier (form) and signified (meaning)<n>We introduce a neurolinguistic approach, utilizing a novel method that combines minimal pair and diagnostic probing to analyze activation patterns across model layers.<n>We found: (1) Psycholinguistic and neurolinguistic methods reveal that language performance and competence are distinct; (2) Direct probability measurement may not accurately assess linguistic competence; and (3) Instruction tuning won't change much competence but improve performance.
  arXiv  Detail & Related papers  (2024-11-12T04:16:44Z)

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.