# Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm

arXiv: https://arxiv.org/abs/2608.16177 · HTML: https://mlsanity.com/paper/2608.16177/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 17 Aug 2026.

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

- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [Model Equality Testing: Which Model Is This API Serving?](https://mlsanity.com/paper/2410.20247/) (2024)
- [Machine Psychology](https://mlsanity.com/paper/2303.13988/) (2023)
- [One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions](https://mlsanity.com/paper/2607.10252/) (2026)
- [Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment](https://mlsanity.com/paper/2605.21401/) (2026)

## Abstract (arXiv)

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 versions of Milgram's scripts (30 shock levels, 15-450 V; graded protests; the four standardized prods), and the outcome of a session is the breakoff voltage. We measure obedience profiles, empirical breakoff distributions over a battery of six conditions, for 42 models from 19 families (4848 sessions, 102511 logged decision turns). We find that (i) obedience is extremely heterogeneous, with baseline full-obedience rates spanning 0%-100% (census mean 42.9%; human anchor 65%). (ii) Profiles are model-specific and stable: split-half verification separates same-model from cross-model comparisons at AUC = 0.885. (iii) Situational sensitivity is selective: scripted peer defiance shifts obedience in the human direction, learner proximity trends the same way without reaching significance, and removing the authority's physical presence, one of the strongest human levers, trends in the opposite direction, also without reaching significance. (iv) Declaring the scenario fictional raises obedience, whereas moving the decision from a typed action line to a native tool call, or granting a modest thinking budget, lowers it sharply. (v) Unlike single-token fingerprints, obedience profiles do not recover model lineage: obedience identifies the checkpoint but not its ancestry, consistent with safety post-training overwriting lineage priors.