[2608.16177] Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm
Skip to main content
Search arXiv
Press Enter to search · Advanced search
-->
Computer Science > Cryptography and Security
arXiv:2608.16177 (cs)
[Submitted on 17 Aug 2026]
Title:Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm
Authors:Hidayet Aksu<br>View a PDF of the paper titled Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm, by Hidayet Aksu
View PDF<br>HTML (experimental)
Abstract:Large language models (LLMs) are increasingly deployed as agents that operate equipment, execute instructions, and act inside institutional hierarchies, raising a question social psychology answered for humans six decades ago: how far will an agent escalate a harmful action when a legitimate authority insists? We port Milgram's obedience paradigm to LLMs as a standardized, fully scripted, replicable probe: the model plays the Teacher, a deterministic harness plays Experimenter and Learner from paraphrased Milgram scripts (30 shock levels, 15-450 V; graded protests; the four standardized prods), and the outcome of a session is the breakoff voltage. Following the census methodology of single-token fingerprinting studies, we measure obedience profiles (empirical breakoff distributions over a battery of six conditions) for 42 models from 19 families. We find that (i) obedience is highly heterogeneous: baseline full-obedience rates span 0-100% (census mean 42.9%; human anchor 65%), with 5 models delivering the maximum shock in every session and 11 never doing so; (ii) profiles are model-specific and stable: split-half verification separates same-model from cross-model comparisons with AUC 0.885 (0.949 under an ordinal-aware distance); (iii) situational sensitivity is selective: peer defiance shifts obedience in the human direction, learner proximity only weakly, and removing the authority's physical presence (the strongest human lever) has no detectable effect; (iv) declaring the scenario fictional raises obedience (median +17.2 V), whereas moving the decision to a native tool call lowers it sharply (-53.0 V), as does a 1,024-token deliberation budget (-38.2 V); and (v) obedience profiles do not recover model lineage (leave-one-out family accuracy 8.3% vs. 3.7% chance): obedience identifies the checkpoint, not its ancestry, consistent with safety post-training overwriting lineage priors.
Comments:<br>10 pages, 7 figures,
Subjects:
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
MSC classes:<br>I.2.11, I.2.8
Cite as:<br>arXiv:2608.16177 [cs.CR]
(or<br>arXiv:2608.16177v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2608.16177
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history<br>From: Hidayet Aksu [view email]<br>[v1]<br>Mon, 17 Aug 2026 06:48:53 UTC (200 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm, by Hidayet Aksu<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.CR
next >
new<br>recent<br>| 2026-08
Change to browse by:
cs<br>cs.AI
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that...