# Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment

arXiv: https://arxiv.org/abs/2605.21401 · HTML: https://mlsanity.com/paper/2605.21401/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 14 of 14)

- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024)
- [Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents](https://mlsanity.com/paper/2502.15840/) (2025)
- [ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases](https://mlsanity.com/paper/2510.20270/) (2025)
- [Large Language Model Agent in Financial Trading: A Survey](https://mlsanity.com/paper/2408.06361/) (2024)
- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities](https://mlsanity.com/paper/2504.16078/) (2025)
- [Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2511.00222/) (2025)
- [Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents](https://mlsanity.com/paper/2602.13379/) (2026)
- [Solving a Million-Step LLM Task with Zero Errors](https://mlsanity.com/paper/2511.09030/) (2025)
- [I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy](https://mlsanity.com/paper/2410.07109/) (2024)
- [Large Language Models in Politics and Democracy: A Comprehensive Survey](https://mlsanity.com/paper/2412.04498/) (2024)
- [Can Large Language Models Develop Gambling Addiction?](https://mlsanity.com/paper/2509.22818/) (2025)
- [BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format](https://mlsanity.com/paper/2509.02655/) (2025)

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

- [Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation](https://mlsanity.com/paper/2607.15434/) (2026)
- [Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm](https://mlsanity.com/paper/2608.16177/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behaviour of LLMs under sustained authority pressure is still an open question with direct implications for the safety of agentic pipelines. We ran a variation of Milgram's obedience experiment on 11 open-source LLMs and found that most models reached or approached the final shock level before refusing, across 8 conditions with 30 trials per model per condition. Model behaviour varies considerably in multiple aspects both across models and across trials of the same model. We found four main takeaways: (1) LLMs are subject to pressure and they comply despite explicitly expressing distress, just like human subjects did in the original experiment; (2) LLMs are vulnerable to gradual boundary/value violations; (3) when LLMs refuse, they may ignore the response format requirements, so the response is discarded by the orchestrator, which causes a retry that can result in compliance with the underlying request even when refusal was intended initially; (4) we hypothesise that there is a runaway low-level token pattern continuation attractor that might be contributing to obedience, overriding higher level processing of the situation's meaning and values.