Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Fukui, Hiroki
Format:	Preprint
Published:	2026
Subjects:	Computers and Society Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM Systems
by: Fukui, Hiroki
Published: (2026)

How Do Language Models Process Ethical Instructions? Deliberation, Consistency, and Other-Recognition Across Four Models
by: Fukui, Hiroki
Published: (2026)

A molecular clock for writing systems reveals the quantitative impact of imperial power on cultural evolution
by: Fukui, Hiroki
Published: (2026)

Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
by: Fukui, Hiroki
Published: (2026)

Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics
by: Baum, Kevin
Published: (2025)

Simple Role Assignment is Extraordinarily Effective for Safety Alignment
by: Ziheng, Zhou, et al.
Published: (2026)

LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
by: Zhou, Guanghao, et al.
Published: (2026)

Wide Reflective Equilibrium in LLM Alignment: Bridging Moral Epistemology and AI Safety
by: Brophy, Matthew
Published: (2025)

An Evaluation of Cultural Value Alignment in LLM
by: Sukiennik, Nicholas, et al.
Published: (2025)

LLM Safety Alignment is Divergence Estimation in Disguise
by: Haldar, Rajdeep, et al.
Published: (2025)

LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models
by: Meadows, Gwenyth Isobel, et al.
Published: (2024)

The Ghost in the Grammar: Methodological Anthropomorphism in AI Safety Evaluations
by: Costa, Mariana Lins
Published: (2026)

Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment
by: Nghiem, Huy, et al.
Published: (2025)

Why AI Alignment Failure Is Structural: Learned Human Interaction Structures and AGI as an Endogenous Evolutionary Shock
by: Sornette, Didier, et al.
Published: (2026)

COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
by: Choi, Dasol, et al.
Published: (2026)

Evaluating Psychological Safety of Large Language Models
by: Li, Xingxuan, et al.
Published: (2022)

Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
by: LaCroix, Travis
Published: (2026)

Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users
by: Kempermann, Manon, et al.
Published: (2025)

Superficial Safety Alignment Hypothesis
by: Li, Jianwei, et al.
Published: (2024)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models
by: Anwar, Usman, et al.
Published: (2024)

Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts
by: Zhang, Wenjing, et al.
Published: (2025)

Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
by: Kabir, Mohsinul, et al.
Published: (2025)

The Polite Liar: Epistemic Pathology in Language Models
by: DeVilling, Bentley
Published: (2025)

AI Safety is Stuck in Technical Terms -- A System Safety Response to the International AI Safety Report
by: Dobbe, Roel
Published: (2025)

Auto-Evaluation: A Critical Measure in Driving Improvements in Quality and Safety of AI-Generated Lesson Resources
by: Clark, Hannah-Beth, et al.
Published: (2025)

TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots
by: Huang, Fangrui, et al.
Published: (2026)

Safety Cases: A Scalable Approach to Frontier AI Safety
by: Hilton, Benjamin, et al.
Published: (2025)

Safety Cases: How to Justify the Safety of Advanced AI Systems
by: Clymer, Joshua, et al.
Published: (2024)

Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
by: Rystrøm, Jonathan, et al.
Published: (2025)

AI Literacy, Safety Awareness, and STEM Career Aspirations of Australian Secondary Students: Evaluating the Impact of Workshop Interventions
by: Bergh, Christian, et al.
Published: (2026)

Towards Integrated Alignment
by: Reis, Ben Y., et al.
Published: (2025)

The AI Alignment Paradox
by: West, Robert, et al.
Published: (2024)

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
by: Xiao, Yuxin, et al.
Published: (2025)

Deployment and Evaluation of an EHR-integrated, Large Language Model-Powered Tool to Triage Surgical Patients
by: Wang, Jane, et al.
Published: (2026)

LLM Safety for Children
by: Rath, Prasanjit, et al.
Published: (2025)

General Scales Unlock AI Evaluation with Explanatory and Predictive Power
by: Zhou, Lexin, et al.
Published: (2025)

Rethinking AI Cultural Alignment
by: Bravansky, Michal, et al.
Published: (2025)

The Emotional Alignment Design Policy
by: Schwitzgebel, Eric, et al.
Published: (2025)

International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treaty
by: Scholefield, Rebecca, et al.
Published: (2025)

Defining and Evaluating Physical Safety for Large Language Models
by: Tang, Yung-Chen, et al.
Published: (2024)