How Ethical Should AI Be? How AI Alignment Shapes the Risk Preferences of LLMs.
Shumiao OuyangHayong YunXingjian ZhengPublished in: CoRR (2024)
Keyphrases
- artificial intelligence
- expert systems
- ai systems
- case based reasoning
- intelligent behavior
- decision making
- knowledge representation
- knowledge based systems
- intelligent systems
- lecture notes in artificial intelligence
- object recognition
- john mccarthy
- principal axes
- ai community
- ai technologies
- shape recognition
- high risk
- shape descriptors
- machine intelligence
- dynamic time warping
- shape matching
- data sets
- user preferences
- logic programming
- computational intelligence
- machine learning