Code and data for our IROS paper: "Are Large Language Models Aligned with People's Social Intuitions for Human–Robot Interactions?"
-
Updated
Mar 20, 2025 - Jupyter Notebook
#
value-alignment
Here are 5 public repositories matching this topic...
EthosGPT is an open-source framework that maps how Large Language Models align with diverse human values, promoting cultural and ethical diversity in AI-driven decision-making.
python html plotly render dash html-css matplotlib html-css-javascript human-values ethical-ai open-source-framework large-language-models value-alignment ethosgpt cultural-diversity ethical-diversity ai-decision-making societal-innovation sustainable-progress
-
Updated
Nov 24, 2024 - Jupyter Notebook
PRISM: A Multi-Perspective AI Alignment Framework for Ethical AI (Demo: https://app.prismframework.ai | Paper: https://arxiv.org/abs/2503.04740)
machine-learning reinforcement-learning cognitive-science multi-objective-optimization ai-alignment ethical-ai large-language-models value-alignment computational-ethics llm-integration multi-perspective-reasoning pareto-optimization
-
Updated
Mar 10, 2025 - TypeScript
A comprehensive toolkit for implementing, analyzing, and validating AI value alignment based on Anthropic's 'Values in the Wild' research.
-
Updated
Apr 30, 2025 - Python
A data-driven framework mapping daily activities to multi-horizon goals, exploring time-to-value realization beyond traditional 80/20 optimization
-
Updated
Feb 3, 2025
Improve this page
Add a description, image, and links to the value-alignment topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the value-alignment topic, visit your repo's landing page and select "manage topics."