面向中文大模型价值观的评估与对齐研究
-
Updated
Jul 20, 2023 - Python
#
human-values
Here are 3 public repositories matching this topic...
Machine Learning scripts for the identification of human values behind arguments.
-
Updated
Mar 12, 2024 - Python
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
Jul 18, 2026 - Python
Improve this page
Add a description, image, and links to the human-values topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the human-values topic, visit your repo's landing page and select "manage topics."