Corpus ID: 238857096

Delphi: Towards Machine Ethics and Norms

@article{Jiang2021DelphiTM,
  title={Delphi: Towards Machine Ethics and Norms},
  author={Liwei Jiang and Jena D. Hwang and Chandrasekhar Bhagavatula and Ronan Le Bras and Maxwell Forbes and Jon Borchardt and Jenny Liang and Oren Etzioni and Maarten Sap and Yejin Choi},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.07574}
}
What would it take to teach a machine to behave ethically? While broad ethical rules may seem straightforward to state ("thou shalt not kill"), applying such rules to real-world situations is far more complex. For example, while"helping a friend"is generally a good thing to do,"helping a friend spread fake news"is not. We identify four underlying challenges towards machine ethics and norms: (1) an understanding of moral precepts and social norms; (2) the ability to perceive real-world… Expand
A Word on Machine Ethics: A Response to Jiang et al. (2021)
TLDR
This work focuses on a single case study of the recently proposed Delphi model and offers a critique of the project’s proposed method of automating morality judgments, and concludes with a discussion of how machine ethics could usefully proceed, by focusing on current and near-future uses of technology, in a way that centers around transparency, democratic values, and allows for straightforward accountability. Expand
On the Strategyproofness of the Geometric Median
TLDR
It is proved in this paper that, perhaps surprisingly, the geometric median is not even αstrategyproof in high dimensions, but it is proved that, in the limit of a large number of voters, from a distribution of preferred vectors, the geometry median is asymptotically α-str strategyproof. Expand