Skip to content
#

human-value-alignment

Star

Here are 2 public repositories matching this topic...

biological-alignment-benchmarks / milgram-for-llms

Star 2

Four main takeaways: (1) LLMs are subject to pressure, they comply despite expressing distress; (2) LLMs are vulnerable to gradual boundary/value violations; (3) when LLMs refuse, they may ignore the response format requirements, so the query is retried; (4) we hypothesise there is a token pattern continuation attractor that might cause obedience.

benchmark evaluation balancing eval multi-objective social-psychology human-values multi-turn large-language-models obedience value-alignment human-value-alignment obedience-and-conformity safety-constraints milgram runaway-agent
  • Updated May 26, 2026
  • Python

Improve this page

Add a description, image, and links to the human-value-alignment topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the human-value-alignment topic, visit your repo's landing page and select "manage topics."

Learn more